© 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. 16257
    Prev
    Next
    INDEX
    Explanations

    project structure, modules, and config

    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
     aprecia
    -1.15
     oči
    -1.05
     maquiagem
    -1.05
     antichi
    -1.05
     offizi
    -0.99
    撵
    -0.96
     tatuagem
    -0.96
     posesión
    -0.95
     maneiras
    -0.94
     enfrentan
    -0.94
    POSITIVE LOGITS
     Color
    0.92
     caracter
    0.92
     antes
    0.91
     enci
    0.91
    ve
    0.91
     Beding
    0.89
     включа
    0.89
    zedł
    0.88
     GF
    0.88
     local
    0.87
    Activations Density 0.006%

    No Known Activations