© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65786
    Prev
    Next
    INDEX
    Explanations

    collection select, testing assertions

    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
    麋
    -0.75
     quedado
    -0.75
    liament
    -0.73
     derfor
    -0.72
    usaha
    -0.71
    Comer
    -0.71
     autorisé
    -0.71
    ▓
    -0.71
     ruptura
    -0.71
    jalan
    -0.71
    POSITIVE LOGITS
    references
    0.94
     integer
    0.92
    integer
    0.84
     Delegates
    0.81
    timestamps
    0.79
     belong
    0.78
    degenerate
    0.78
    string
    0.75
    ervazione
    0.75
     redraw
    0.74
    Activations Density 0.004%

    No Known Activations