© 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. 10-GEMMASCOPE-RES-131K
    7. 103543
    Prev
    Next
    INDEX
    Explanations

    specifying dates

    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
    とその
    -2.02
    enuto
    -2.02
    ника
    -1.97
    沄
    -1.90
    柺
    -1.89
    вую
    -1.88
    𐌽
    -1.87
    矍
    -1.84
     conç
    -1.80
     Что
    -1.79
    POSITIVE LOGITS
    of
    2.89
     the
    2.89
    —
    2.22
    '
    2.20
     của
    2.08
     insinu
    1.99
     dated
    1.97
    an
    1.93
     verschied
    1.93
    *,
    1.92
    Activations Density 0.010%

    No Known Activations