© 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. 59312
    Prev
    Next
    INDEX
    Explanations

    given name followed by surname

    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
    ет
    -2.48
    ll
    -2.45
    en
    -2.39
    真的是
    -2.31
    </strong>
    -2.16
    we
    -2.11
    just
    -2.05
     votre
    -2.05
    '
    -2.03
    依然
    -2.00
    POSITIVE LOGITS
    獁
    2.77
    ৄ
    2.77
    "]));
    2.70
     the
    2.67
    錞
    2.61
    情况下
    2.55
     哪些
    2.50
    "));
    2.48
    }$,
    2.44
    </td>
    2.38
    Activations Density 0.003%

    No Known Activations