© 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. 118873
    Prev
    Next
    INDEX
    Explanations

    wordpress components

    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
     Havre
    -0.78
     Princeton
    -0.77
    General
    -0.77
    ndag
    -0.75
    agami
    -0.73
     Générale
    -0.72
    dimensional
    -0.72
    Computer
    -0.71
    Princeton
    -0.70
    单
    -0.70
    POSITIVE LOGITS
     Hift
    0.85
    ܦ
    0.77
    linker
    0.77
     foreman
    0.76
    laint
    0.75
    perso
    0.75
    LINKS
    0.74
    sod
    0.73
     gezondheid
    0.73
     diensten
    0.72
    Activations Density 0.021%

    No Known Activations