© 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. 10-GEMMASCOPE-RES-131K
    7. 7386
    Prev
    Next
    INDEX
    Explanations

    various proper nouns

    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_10/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
     丁目
    -2.98
    führende
    -2.81
    婞
    -2.70
    狲
    -2.67
     Senhora
    -2.67
    鶘
    -2.67
    閹
    -2.64
     himſelf
    -2.64
    nipeg
    -2.63
    思议
    -2.59
    POSITIVE LOGITS
    ↵
    4.19
    en
    3.78
    P
    3.67
    S
    3.61
    ar
    3.61
    IN
    3.50
    is
    3.47
    s
    3.41
    M
    3.34
    L
    3.31
    Activations Density 0.044%

    No Known Activations