© 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. 22-GEMMASCOPE-RES-131K
    7. 73329
    Prev
    Next
    INDEX
    Explanations

    specific actions or items

    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
     beslu
    -1.12
     zelen
    -1.03
     będę
    -1.00
     étui
    -1.00
     znaczy
    -0.96
     Nguy
    -0.93
     Traducción
    -0.92
    PaymentMethod
    -0.92
     disposição
    -0.91
     versões
    -0.90
    POSITIVE LOGITS
    cences
    1.09
     faster
    1.02
     tikai
    1.00
    相同
    0.96
     single
    0.94
    ClientSize
    0.92
     quick
    0.92
    ৷
    0.91
    ⎨
    0.91
     or
    0.90
    Activations Density 0.015%

    No Known Activations