© 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. 34-GEMMASCOPE-RES-131K
    7. 109700
    Prev
    Next
    INDEX
    Explanations

    Christ Church College

    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
     sexuales
    -0.79
    並ぶ
    -0.77
     Reduced
    -0.77
    nosotros
    -0.75
    壢
    -0.75
    Lista
    -0.74
     隊
    -0.73
    playera
    -0.73
    ނ
    -0.72
     画面
    -0.72
    POSITIVE LOGITS
    pher
    0.95
    ansen
    0.84
     equations
    0.81
     Chris
    0.77
     cleared
    0.77
    opher
    0.77
    Jing
    0.77
     Christ
    0.77
    ened
    0.76
    COMPAR
    0.76
    Activations Density 0.010%

    No Known Activations