© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19230
    Prev
    Next
    INDEX
    Explanations

    foreign titles and proper nouns

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

    glucose, Science, range, burn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    рок
    0.56
    릇
    0.56
    стым
    0.52
    rét
    0.51
     ஏற்பட
    0.50
    肮
    0.48
    鲢
    0.47
     жизнен
    0.46
    >);
    0.46
    lą
    0.46
    POSITIVE LOGITS
     นาย
    0.48
    氏は
    0.47
    ვით
    0.45
     Başkan
    0.44
    are
    0.44
     Nazionale
    0.43
     Bakan
    0.43
     veya
    0.43
     estuvo
    0.43
     नगरपालिका
    0.42
    Activations Density 0.001%

    No Known Activations