© 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. 112467
    Prev
    Next
    INDEX
    Explanations

    list of items followed by etc

    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
    dă
    -1.51
    delaide
    -1.50
    ydın
    -1.49
    瀦
    -1.48
     Sünde
    -1.45
    ჱ
    -1.45
    kval
    -1.44
    ająca
    -1.43
    nă
    -1.40
     devriez
    -1.40
    POSITIVE LOGITS
    y
    2.31
    in
    1.89
    k
    1.77
    a
    1.74
    h
    1.72
    c
    1.70
    at
    1.68
    w
    1.67
    is
    1.65
    v
    1.64
    Activations Density 0.037%

    No Known Activations