© 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. 9519
    Prev
    Next
    INDEX
    Explanations

    Regina, Hubert, Quint, Randall, XV

    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
    s
    -3.73
    *
    -3.64
    “
    -3.36
    ter
    -3.22
    c
    -3.13
    『
    -3.02
    er
    -2.95
    \
    -2.92
    n
    -2.91
    is
    -2.89
    POSITIVE LOGITS
    却又
    2.84
    昻
    2.73
    鹋
    2.70
    閡
    2.63
    fí
    2.53
    过头
    2.52
    ٶ
    2.48
    惕
    2.44
     می‌
    2.42
    祧
    2.41
    Activations Density 0.012%

    No Known Activations