© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107903
    Prev
    Next
    INDEX
    Explanations

    muscle, lifts, years, is, podcast

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

    The neuron fires on claims that a small set of exercises (often “three lifts”) will cover or target all major muscle groups.

    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
    configura
    -0.88
     zemi
    -0.86
     شدند
    -0.77
    relax
    -0.75
     молит
    -0.74
    続ける
    -0.73
    finger
    -0.73
     Koen
    -0.73
     يه
    -0.72
     thăm
    -0.71
    POSITIVE LOGITS
     stabilis
    0.81
     Kettle
    0.79
     mid
    0.79
     Prim
    0.78
     ogó
    0.78
     głównie
    0.77
     international
    0.77
     Mid
    0.77
     международ
    0.75
    ダー
    0.74
    Activations Density 0.016%

    No Known Activations