© 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. 11703
    Prev
    Next
    INDEX
    Explanations

    physical aspects

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

    This neuron activates whenever the word “physical” (in any capitalization or part of a technical phrase like “Physical Optics”) appears.

    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
     puma
    0.56
     MFG
    0.56
     пород
    0.55
    違
    0.55
     Yoruba
    0.55
    轮回
    0.54
    ♝
    0.54
    ඩ්
    0.53
     magist
    0.53
    ఞ
    0.53
    POSITIVE LOGITS
    Physical
    1.01
     Physical
    0.98
    physical
    0.98
     physical
    0.95
     फिजिकल
    0.88
     физи
    0.87
     fysis
    0.84
     Physically
    0.82
     PHYSICAL
    0.81
     fís
    0.80
    Activations Density 0.100%

    No Known Activations