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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 604
    Prev
    Next
    INDEX
    Explanations

    code structure

    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
     costumbres
    -2.34
    茈
    -2.22
    儅
    -2.02
     ralla
    -1.98
    閖
    -1.97
     vôtre
    -1.94
     éc
    -1.93
     mété
    -1.91
    ︐
    -1.90
     tirantes
    -1.88
    POSITIVE LOGITS
     to
    2.73
     in
    2.69
     that
    2.55
     It
    2.44
     for
    2.19
    𓋼
    2.14
     on
    2.06
    ྜ
    2.00
    ;
    2.00
    不宜
    2.00
    Activations Density 0.005%

    No Known Activations