© 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. 129043
    Prev
    Next
    INDEX
    Explanations

    vial, Sampson, ETL, midline

    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
    媖
    -3.11
    榈
    -3.02
    ть
    -2.69
    改装
    -2.64
    蹌
    -2.58
    峮
    -2.56
    之色
    -2.50
    鎘
    -2.44
     contado
    -2.39
    薦
    -2.39
    POSITIVE LOGITS
     \
    3.30
    ly
    2.75
    i
    2.66
    硖
    2.56
    the
    2.47
    ="
    2.45
     '
    2.42
    h
    2.39
    c
    2.38
     když
    2.31
    Activations Density 0.012%

    No Known Activations