© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127276
    Prev
    Next
    INDEX
    Explanations

    start of a section

    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
    も多く
    -1.91
    囘
    -1.77
     продолжает
    -1.76
     cambió
    -1.69
    さんも
    -1.63
     representado
    -1.63
     involucrados
    -1.60
    itsubishi
    -1.59
     habrá
    -1.59
     deux
    -1.55
    POSITIVE LOGITS
     of
    2.16
    琹
    1.70
     入れ
    1.67
     "}";
    1.66
     help
    1.65
     ४
    1.63
     (
    1.63
    ِّف
    1.63
    </tfoot>
    1.62
    $,
    1.59
    Activations Density 0.002%

    No Known Activations