© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 73757
    Prev
    Next
    INDEX
    Explanations

    code imports and definitions

    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
     Auguste
    -0.80
    vados
    -0.77
     actions
    -0.74
     ings
    -0.73
     services
    -0.73
    magnes
    -0.73
    actions
    -0.71
    userService
    -0.71
     acciones
    -0.70
    tts
    -0.70
    POSITIVE LOGITS
    跛
    0.82
     combineReducers
    0.81
     HISTORY
    0.81
    Immer
    0.75
    Madre
    0.73
    redux
    0.72
    joit
    0.72
    のではないか
    0.71
     histories
    0.71
     Produto
    0.71
    Activations Density 0.011%

    No Known Activations