© 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. 12186
    Prev
    Next
    INDEX
    Explanations

    location and specific details

    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
    stdafx
    -0.81
    TECN
    -0.81
    īg
    -0.80
     metá
    -0.79
    Clusters
    -0.78
    ванні
    -0.77
     sqm
    -0.75
     ••
    -0.75
    EventEmitter
    -0.75
     Equi
    -0.75
    POSITIVE LOGITS
     geographical
    0.96
     personalized
    0.95
     contextual
    0.93
     geographic
    0.92
     connect
    0.90
    特定
    0.89
     personalised
    0.89
    なんだろう
    0.88
     local
    0.86
     connecting
    0.86
    Activations Density 0.183%

    No Known Activations