© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 16959
    Prev
    Next
    INDEX
    Explanations

    arm, elbow, and wrist

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

    biceps, elbow, arm movement

    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_53_width_65k_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
     legs
    0.85
     Legs
    0.79
    legs
    0.76
    腿
    0.74
    脚
    0.72
     piernas
    0.68
     leg
    0.64
     jambes
    0.64
     ноги
    0.63
    腳
    0.63
    POSITIVE LOGITS
     elbow
    1.92
    elbow
    1.77
     forearm
    1.63
     Elbow
    1.63
    肘
    1.59
     elbows
    1.49
     arm
    1.44
     biceps
    1.34
     wrist
    1.30
    腕
    1.29
    Activations Density 0.069%

    No Known Activations