© 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. 128326
    Prev
    Next
    INDEX
    Explanations

    courage, bravery, courageously

    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
     ४
    -1.84
     煮
    -1.80
    梱
    -1.76
    '
    -1.76
     eſſ
    -1.70
    ＂
    -1.70
    \"
    -1.66
    閙
    -1.65
     殺
    -1.63
     roligt
    -1.62
    POSITIVE LOGITS
    8
    2.13
    6
    2.02
    来ました
    1.91
    7
    1.78
    CHREIB
    1.78
    帰る
    1.77
    戋
    1.74
    動か
    1.73
    行きます
    1.72
    不愿意
    1.66
    Activations Density 0.019%

    No Known Activations