© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3207
    Prev
    Next
    INDEX
    Explanations

    Ruby, Rails

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on technical tokens such as URLs, code repository paths, and programming‐related identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical documentation and code snippets, particularly related to Ruby on Rails, configuration files, and programming tutorials.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to software development and DevOps artifacts, including code/configuration snippets, repository/commit links, and build/runtime error messages.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uv
    0.60
    PanelVisual
    0.57
     Influence
    0.52
     вне
    0.51
     заключается
    0.51
    impinan
    0.51
    auga
    0.51
    醴
    0.51
     axial
    0.50
     UV
    0.50
    POSITIVE LOGITS
     Rails
    1.77
    Rails
    1.76
    rails
    1.46
     rails
    1.45
     "#{
    1.40
    ("#{
    1.36
     Ruby
    1.34
     ActiveRecord
    1.29
    Ruby
    1.28
     ruby
    1.25
    Activations Density 0.019%

    No Known Activations