© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108037
    Prev
    Next
    INDEX
    Explanations

    lower body parts

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

    The neuron flags mentions of body‐part locations or levels—phrases that specify anatomical sites or extents (e.g. “at the thigh level,” “below the knees,” “up to her knee”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     wings
    -0.82
    nościo
    -0.79
    лио
    -0.75
     yeux
    -0.71
    arms
    -0.70
     Tamp
    -0.69
     Администра
    -0.69
    Admin
    -0.68
    utados
    -0.68
    ungs
    -0.68
    POSITIVE LOGITS
     ankle
    2.69
     ankles
    2.19
     calf
    1.91
    ankle
    1.91
     knee
    1.79
     calves
    1.70
     Ankle
    1.69
     wrist
    1.55
     Calf
    1.41
     shin
    1.35
    Activations Density 0.044%

    No Known Activations