© 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. 32472
    Prev
    Next
    INDEX
    Explanations

    tighten screws bolts nuts

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

    The neuron activates on terms and phrases describing the mechanical action of tightening or loosening fasteners (bolts, nuts, couplings, etc.).

    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
    Wednesday
    -0.82
    лам
    -0.81
    Tuesday
    -0.80
    Sydney
    -0.80
    Mil
    -0.78
    boxy
    -0.75
    Daddy
    -0.74
     préparation
    -0.74
    ename
    -0.74
    loyed
    -0.74
    POSITIVE LOGITS
     screws
    2.86
     bolts
    2.39
     screw
    2.30
     nuts
    2.27
     bolt
    1.95
     nut
    1.95
     Screws
    1.88
     Nuts
    1.72
     Bolts
    1.70
    screw
    1.66
    Activations Density 0.032%

    No Known Activations