© 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. 58478
    Prev
    Next
    INDEX
    Explanations

    documentation and code snippets

    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
     mélange
    -0.82
    ってます
    -0.81
    سكرية
    -0.76
     Docks
    -0.76
    жок
    -0.73
    譙
    -0.73
    Tabela
    -0.73
    věd
    -0.73
     trivial
    -0.72
     睡
    -0.72
    POSITIVE LOGITS
     attr
    0.81
     string
    0.80
    public
    0.80
    いち
    0.77
     IDS
    0.75
    IDS
    0.75
    िने
    0.74
     스타일
    0.74
     PLO
    0.73
    wira
    0.73
    Activations Density 0.001%

    No Known Activations