© 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. 39524
    Prev
    Next
    INDEX
    Explanations

    key access

    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
    </h3>
    -3.66
    ↵
    -3.42
    .
    -2.98
    ’
    -2.89
    "
    -2.77
    $
    -2.69
    </sub>
    -2.66
     jeopardi
    -2.61
    ”,
    -2.58
    ^{+}\
    -2.55
    POSITIVE LOGITS
     setelah
    2.92
    ጁ
    2.84
    샅
    2.73
    ‪.‬‬
    2.70
     ПРО
    2.67
     expérimentés
    2.66
    鮠
    2.64
    最初の
    2.64
    是非常
    2.63
     炒め
    2.59
    Activations Density 0.032%

    No Known Activations