© 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. 38887
    Prev
    Next
    INDEX
    Explanations

    New Orleans Saints, cuisine, police

    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
    廰
    -1.80
    un
    -1.72
     the
    -1.66
    サーバー
    -1.66
    苼
    -1.63
     noirs
    -1.62
     Оно
    -1.59
    (!)
    -1.58
    <bos>
    -1.53
    ung
    -1.52
    POSITIVE LOGITS
    ’
    2.14
    atified
    1.59
    ’，
    1.48
    徕
    1.44
    larda
    1.38
     novelist
    1.38
    壜
    1.38
    tieve
    1.38
    цене
    1.38
     дерево
    1.34
    Activations Density 0.013%

    No Known Activations