© 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. 58541
    Prev
    Next
    INDEX
    Explanations

    file uri and omitted sections

    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
     शुर
    -1.89
    轫
    -1.79
    堕
    -1.79
    炬
    -1.74
    一刻
    -1.70
     车
    -1.70
    钲
    -1.68
    軔
    -1.68
    ༈
    -1.67
    鸲
    -1.63
    POSITIVE LOGITS
    indd
    2.19
    s
    2.03
    (
    2.02
    I
    1.86
     totalmente
    1.78
    櫺
    1.76
     تمامی
    1.73
    )
    1.71
     Incorpor
    1.70
     Impressive
    1.66
    Activations Density 0.001%

    No Known Activations