© 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. 22-GEMMASCOPE-RES-131K
    7. 11374
    Prev
    Next
    INDEX
    Explanations

    counting sequences

    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_22/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
    也要
    -1.08
    白的
    -1.04
     InputMaybe
    -1.02
     órg
    -1.02
     eki
    -0.97
     Other
    -0.96
    τες
    -0.96
     atak
    -0.96
    nibus
    -0.96
     vitaminas
    -0.95
    POSITIVE LOGITS
     roślin
    1.23
     then
    1.11
     személy
    1.08
     comprometido
    0.96
    時から
    0.96
     Standort
    0.96
    rousel
    0.95
    ५
    0.93
    imų
    0.93
    /*
    0.92
    Activations Density 0.010%

    No Known Activations