© 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. 74915
    Prev
    Next
    INDEX
    Explanations

    code identifiers and methods

    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
     OGSÅ
    -1.96
     acompañ
    -1.96
    lección
    -1.91
    逦
    -1.88
     clasificación
    -1.83
    \
    -1.82
    ichtete
    -1.78
    ция
    -1.77
    føl
    -1.75
    鴆
    -1.74
    POSITIVE LOGITS
     not
    1.95
    ing
    1.91
    t
    1.91
    w
    1.89
    ul
    1.85
     the
    1.80
     thật
    1.75
    k
    1.73
    u
    1.71
    om
    1.65
    Activations Density 0.018%

    No Known Activations