© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8180
    Prev
    Next
    INDEX
    Explanations

    programming syntax or code keywords

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

    This neuron fires on key Ruby on Rails controller action tokens—method names and keywords like `render`, `params`, `format`, `respond_to`, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    话音
    -1.55
     \
    -1.52
    borderSide
    -1.50
    脔
    -1.48
     Erwä
    -1.46
     \
    -1.44
    走吧
    -1.41
    迎来
    -1.38
    \
    -1.33
    椟
    -1.33
    POSITIVE LOGITS
     to
    2.03
     out
    1.66
    s
    1.51
     including
    1.40
     like
    1.40
     the
    1.38
     خالد
    1.36
    romatic
    1.30
    gebir
    1.29
    y
    1.25
    Activations Density 0.005%

    No Known Activations