© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48360
    Prev
    Next
    INDEX
    Explanations

    begin code blocks

    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_10/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
    艄
    -1.77
    vantaged
    -1.76
    髫
    -1.70
    ⚣
    -1.70
     และ
    -1.69
    en
    -1.68
     amd
    -1.68
     hlavně
    -1.66
    atr
    -1.66
     și
    -1.66
    POSITIVE LOGITS
     when
    2.45
    Despite
    1.78
    .
    1.66
     brevemente
    1.66
     during
    1.65
    kových
    1.57
    dengar
    1.54
    擽
    1.52
     Проци
    1.52
     ésta
    1.49
    Activations Density 0.007%

    No Known Activations