© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110764
    Prev
    Next
    INDEX
    Explanations

    muscular contractions and Tobias names

    np_acts-logits-general · gemini-2.5-flash-lite

    words related to muscles or muscular systems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    1
    -2.92
    '
    -2.91
    0
    -2.83
    栳
    -2.52
    アマ
    -2.33
    先生の
    -2.30
    About
    -2.28
     et
    -2.22
    籥
    -2.16
    Our
    -2.13
    POSITIVE LOGITS
    k
    2.77
    سجيلات
    2.75
    n
    2.38
    」
    2.36
    一定的
    2.34
    >`;
    2.33
    手で
    2.30
    dzić
    2.30
    ſſer
    2.30
     глазах
    2.28
    Activations Density 0.005%

    No Known Activations