© 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. 99181
    Prev
    Next
    INDEX
    Explanations

    names like Chand, Chandler, Alexandre, Chandra

    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
    ⼥
    -2.61
     was
    -2.59
    replyreport
    -2.44
    遑
    -2.39
     l
    -2.33
    );
    -2.17
    0
    -2.16
    brinco
    -2.13
    ㌘
    -2.11
     also
    -2.09
    POSITIVE LOGITS
    ate
    3.00
    ar
    2.98
    $,
    2.97
    薷
    2.89
    t
    2.72
     were
    2.69
    of
    2.67
    嫆
    2.59
     męska
    2.56
     besseren
    2.33
    Activations Density 0.002%

    No Known Activations