© 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. 10-GEMMASCOPE-RES-131K
    7. 58055
    Prev
    Next
    INDEX
    Explanations

    multilingual content

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

    This neuron spotlights stative or passive verb forms (e.g., “shown,” “developed,” “есть”).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Ꮷ
    -1.98
     pérd
    -1.92
     that
    -1.82
    橚
    -1.81
    aimana
    -1.76
    褙
    -1.75
    ﹍﹍
    -1.68
    泚
    -1.59
    颏
    -1.59
     the
    -1.57
    POSITIVE LOGITS
     a
    4.03
     an
    2.33
     of
    1.97
    ($__
    1.79
    ",
    1.78
    <bos>
    1.76
     was
    1.67
     such
    1.67
     -
    1.65
     has
    1.65
    Activations Density 0.010%

    No Known Activations