Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109958
    Prev
    Next
    INDEX
    Explanations

    composition, reserved, department, bag

    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
    拥
    -0.89
    adze
    -0.88
     sidor
    -0.82
     arsen
    -0.79
    ărilor
    -0.78
    onski
    -0.77
    PHEN
    -0.77
    breng
    -0.76
     Tin
    -0.75
    λος
    -0.75
    POSITIVE LOGITS
    ulso
    0.73
     cump
    0.72
    ytä
    0.70
     whole
    0.70
    しくて
    0.70
    名叫
    0.69
     betrug
    0.66
     ограничи
    0.66
    governmental
    0.66
     Whole
    0.66
    Activations Density 0.003%

    No Known Activations