© 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. 113090
    Prev
    Next
    INDEX
    Explanations

    to the

    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
    6
    -2.20
    ufige
    -2.11
     determinados
    -2.02
     ofrecen
    -1.84
    秾
    -1.80
     renowned
    -1.73
    臯
    -1.73
     głę
    -1.71
     一
    -1.69
     taką
    -1.68
    POSITIVE LOGITS
     by
    2.81
     and
    2.78
    ان
    1.91
     &
    1.91
     as
    1.90
     for
    1.80
     with
    1.73
    ’
    1.64
    𖥦
    1.63
     also
    1.62
    Activations Density 0.185%

    No Known Activations