© 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. 128974
    Prev
    Next
    INDEX
    Explanations

    introduction or clause start

    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
    {
    -3.84
    ir
    -2.75
    ’
    -2.64
    end
    -2.41
    id
    -2.33
    ための
    -2.28
     He
    -2.27
    las
    -2.19
     Prancis
    -2.19
    </strong>
    -2.14
    POSITIVE LOGITS
    蕻
    3.33
    愎
    3.08
    งิน
    2.88
    ༈
    2.88
     were
    2.84
    ︲
    2.77
    轳
    2.72
     комната
    2.67
    嫫
    2.47
    戩
    2.45
    Activations Density 0.000%

    No Known Activations