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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79142
    Prev
    Next
    INDEX
    Explanations

    modes and mechanics

    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
    sofá
    -0.84
    Produit
    -0.83
    resetPassword
    -0.80
     ácido
    -0.77
    Société
    -0.76
    멱
    -0.75
     unjustified
    -0.75
    開封
    -0.75
     Mez
    -0.74
    Killed
    -0.73
    POSITIVE LOGITS
    endientes
    0.94
    import
    0.85
    Communication
    0.85
     parámetros
    0.83
    设施
    0.83
    設施
    0.83
     Snapdragon
    0.82
     ゴールド
    0.82
    要在
    0.82
    CPU
    0.81
    Activations Density 0.016%

    No Known Activations