© 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. 38954
    Prev
    Next
    INDEX
    Explanations

    make a living

    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
     the
    -2.08
     hudeb
    -1.93
    cursions
    -1.88
    䜣
    -1.85
    quirer
    -1.78
    </tfoot>
    -1.77
     türk
    -1.76
    éma
    -1.75
     ними
    -1.75
    粜
    -1.74
    POSITIVE LOGITS
    '
    1.88
    .
    1.86
    [
    1.76
    h
    1.73
    ing
    1.70
    er
    1.66
    o
    1.65
     These
    1.64
    <em>
    1.62
    \\
    1.59
    Activations Density 0.003%

    No Known Activations