© 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. 10-GEMMASCOPE-RES-131K
    7. 111883
    Prev
    Next
    INDEX
    Explanations

    weightlifting and resistance training

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

    The main thing this neuron does is detect mentions of weightlifting or resistance‐training terms (e.g., lifts, presses, deadlift, squat, resistance training).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    h
    -1.98
    v
    -1.95
    O
    -1.90
    f
    -1.77
    p
    -1.69
    _
    -1.66
     {
    -1.66
    ca
    -1.63
    e
    -1.59
    T
    -1.59
    POSITIVE LOGITS
    ⚋
    1.95
    嚶
    1.92
     PUSTAKA
    1.86
    ientras
    1.85
    岨
    1.84
    IBLIO
    1.80
     IBRARY
    1.80
    鹇
    1.80
    彞
    1.78
    圌
    1.75
    Activations Density 0.014%

    No Known Activations