© 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. 16610
    Prev
    Next
    INDEX
    Explanations

    import,

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

    The neuron fires on programming‐language identifiers (class names, method/variable names, import paths, etc.) rather than on ordinary English words.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     два
    -1.09
    ☡
    -1.02
     nyní
    -1.02
    新た
    -1.01
     princípios
    -1.01
     opět
    -1.00
     mostró
    -0.97
    Bjs
    -0.96
    Aç
    -0.95
    RemindMe
    -0.95
    POSITIVE LOGITS
    v
    1.01
    公元
    1.00
    無い
    1.00
    b
    0.98
    h
    0.98
     подозре
    0.97
    ナメント
    0.97
    r
    0.96
    w
    0.95
     Nordrhein
    0.94
    Activations Density 0.014%

    No Known Activations