© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20987
    Prev
    Next
    INDEX
    Explanations

    shoulder and associated anatomy

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

    shoulder shrugs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    দ্দি
    0.53
    </tfoot>
    0.50
     acetaldehyde
    0.50
    សំណ
    0.49
     ноги
    0.48
     участие
    0.48
     巴
    0.48
     القدم
    0.48
     নির্দেশনা
    0.47
     pee
    0.47
    POSITIVE LOGITS
     Shoulder
    0.93
     shoulder
    0.91
    肩
    0.90
     collar
    0.82
    Neck
    0.81
     shoulders
    0.76
     Collar
    0.75
    shoulder
    0.74
    ショルダー
    0.73
     neck
    0.72
    Activations Density 0.050%

    No Known Activations