© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112729
    Prev
    Next
    INDEX
    Explanations

    to + action or destination

    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
     you
    -2.02
     
    -1.90
    呿
    -1.57
    </h3>
    -1.55
     никаких
    -1.45
     [
    -1.45
     рассказыва
    -1.45
     şeyi
    -1.43
    s
    -1.43
     моих
    -1.40
    POSITIVE LOGITS
    鯓
    1.77
    ЛОВ
    1.71
    ZIONE
    1.57
    iempos
    1.55
     of
    1.54
    𓋼
    1.53
    澌
    1.53
    llten
    1.47
     your
    1.45
    elesaikan
    1.43
    Activations Density 0.018%

    No Known Activations