© 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. 15022
    Prev
    Next
    INDEX
    Explanations

    underdog, sidekick, uphill battle

    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
    剮
    -2.19
     '
    -1.73
     If
    -1.72
    小学
    -1.65
    тели
    -1.55
    亙
    -1.53
    اسپ
    -1.53
    青岛
    -1.52
    豋
    -1.52
     and
    -1.52
    POSITIVE LOGITS
    .!
    2.02
    只剩下
    2.00
    彞
    1.98
     determinados
    1.93
    ೢ
    1.91
    橚
    1.91
     ซึ่ง
    1.90
    事が
    1.88
     endeavors
    1.88
    ACCIÓN
    1.82
    Activations Density 0.006%

    No Known Activations