© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2154
    Prev
    Next
    INDEX
    Explanations

    nov, no, но

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     no
    -0.92
    стреча
    -0.90
     pows
    -0.82
    (){
    -0.82
    を
    -0.81
    それから
    -0.79
    後は
    -0.78
    ポイントは
    -0.77
    作品の
    -0.77
     celles
    -0.75
    POSITIVE LOGITS
     šir
    0.94
    ROUND
    0.93
    Nights
    0.91
    yez
    0.90
    Carrying
    0.88
    Ἔ
    0.88
    下記
    0.86
    تام
    0.86
     նաև
    0.86
     protože
    0.86
    Activations Density 0.017%

    No Known Activations