© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64615
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical terms

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

    This neuron responds to code tokens that are function or macro names immediately followed by an opening parenthesis (i.e. function/macro calls).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    anders
    -1.05
    着急
    -0.92
    鐵
    -0.90
     not
    -0.88
     invigor
    -0.86
     accent
    -0.84
    并不
    -0.82
    图片
    -0.82
     دخترانه
    -0.82
     phát
    -0.82
    POSITIVE LOGITS
    leaves
    0.95
     girasol
    0.93
     sacré
    0.93
    آموزش
    0.87
     toneladas
    0.86
    大半
    0.85
    Kilder
    0.85
    嵓
    0.82
    %$
    0.82
    raujo
    0.82
    Activations Density 0.009%

    No Known Activations