© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3265
    Prev
    Next
    INDEX
    Explanations

    meteorological radar, clinical decision

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

    The neuron selectively activates on specialized scientific or biomedical jargon—long domain‐specific technical terms.

    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
    力的
    0.63
    Spacer
    0.61
     आशंका
    0.58
    ╹
    0.58
    više
    0.58
    บุรี
    0.57
    Flair
    0.57
    Needed
    0.56
    Ridge
    0.55
    тить
    0.55
    POSITIVE LOGITS
     laboratories
    0.79
     laboratory
    0.75
     audiovisual
    0.75
     macroeconomic
    0.71
    における
    0.71
     domains
    0.70
     oligonucleotide
    0.70
     domain
    0.69
     contexts
    0.69
     cryptocur
    0.68
    Activations Density 0.494%

    No Known Activations