© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 31813
    Prev
    Next
    INDEX
    Explanations

    body parts and their actions or states

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

    This neuron activates for body parts, particularly extremities like legs, fingers, hands, knees, and shoulders.

    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_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
     itself
    -1.07
     碎
    -0.99
     involving
    -0.96
     of
    -0.96
     in
    -0.94
    わけで
    -0.94
    にします
    -0.89
     ガー
    -0.89
     across
    -0.88
    ၍
    -0.88
    POSITIVE LOGITS
     themselves
    1.55
     которые
    1.45
     and
    1.43
     THANK
    1.11
    ticks
    1.05
    ztes
    1.04
    themselves
    0.99
    ständige
    0.99
     sué
    0.98
    瞟
    0.98
    Activations Density 0.038%

    No Known Activations