© 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. 43955
    Prev
    Next
    INDEX
    Explanations

    unmet family planning

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

    code identifiers preceded by special characters like $, ::, or {} in programming contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on special programming‐ and markup‐style tokens (e.g. PHP’s “::__construct”, “$modules”, “$format”, LaTeX’s “stackrel”, etc.), i.e. it picks out code or math/markup syntax elements.

    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
     to
    -2.66
    哢
    -2.59
    ſtra
    -2.55
    ༀ
    -2.50
     interesan
    -2.28
     juſ
    -2.09
     Berücksich
    -2.09
     męska
    -2.08
     '-')
    -2.06
     вси
    -2.03
    POSITIVE LOGITS
    "
    2.80
     Ensuring
    2.42
    ’
    2.41
     mogą
    2.27
     Similarly
    2.27
     également
    2.23
     solidified
    2.23
    The
    2.23
    ،
    2.22
    },
    2.19
    Activations Density 0.001%

    No Known Activations