© 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. 39101
    Prev
    Next
    INDEX
    Explanations

    acted or enacted laws

    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
    </h1>
    -2.33
    ।
    -2.08
    ୌ
    -2.03
    <
    -2.02
    嵓
    -2.00
    ?
    -2.00
    ;
    -1.98
     inquisitive
    -1.96
     encompass
    -1.96
     ensuing
    -1.93
    POSITIVE LOGITS
     rivista
    2.19
     in
    2.16
     acted
    2.03
    র
    2.02
     剤
    2.02
    𖣘
    1.97
     apoder
    1.95
    栳
    1.94
    褙
    1.94
    ྜ
    1.93
    Activations Density 0.004%

    No Known Activations