© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13940
    Prev
    Next
    INDEX
    Explanations

    defendant

    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
    趿
    -1.95
    archiwizowane
    -1.92
    AddHtmlAttribute
    -1.91
    那么
    -1.89
    acterísticas
    -1.81
    蕻
    -1.76
    z
    -1.74
     oferta
    -1.74
    ,'
    -1.73
    
    -1.73
    POSITIVE LOGITS
    淠
    2.48
    ♪♪
    2.05
    >
    1.99
    勦
    1.92
    𓋼
    1.91
    翌日
    1.87
    最近の
    1.83
    鯔
    1.81
    翾
    1.77
     отсут
    1.73
    Activations Density 0.055%

    No Known Activations