© 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. 59733
    Prev
    Next
    INDEX
    Explanations

    Chang, Changchun, PyeongChang

    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
    韡
    -3.05
    盌
    -2.97
    ྵ
    -2.97
    隂
    -2.89
    🫅
    -2.84
     バッジ
    -2.80
    囖
    -2.77
    狌
    -2.72
     accedi
    -2.70
     広場
    -2.63
    POSITIVE LOGITS
    3
    4.16
    “
    4.13
    6
    3.89
     =
    3.84
    2
    3.83
    1
    3.78
    4
    3.66
    In
    3.61
    an
    3.56
    9
    3.53
    Activations Density 0.003%

    No Known Activations