© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9076
    Prev
    Next
    INDEX
    Explanations

    legs and arteries

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

    The neuron strongly activates on words naming specific garments or fashion pieces.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shoulder
    0.91
     collars
    0.81
    🧥
    0.80
     shoulder
    0.77
     shirts
    0.77
    シャツ
    0.74
     Shirt
    0.74
    Shirt
    0.74
    肩
    0.74
    shoulder
    0.73
    POSITIVE LOGITS
     leg
    1.70
    腿
    1.70
     thigh
    1.60
     legs
    1.57
     thighs
    1.43
    Leg
    1.41
     legg
    1.38
     knee
    1.37
     Leg
    1.35
     Legs
    1.34
    Activations Density 0.370%

    No Known Activations