© 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. 24-GEMMASCOPE-2-RES-16K
    7. 10209
    Prev
    Next
    INDEX
    Explanations

    classic summer

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

    The neuron fires on instructional/navigation cue words (e.g. “above,” “switching,” “button”) that guide readers through steps or interface elements.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ీల
    0.75
     lẽ
    0.70
    ंगी
    0.70
     représentants
    0.68
    人气
    0.67
     espe
    0.66
    低的
    0.66
    ifs
    0.65
    $^{
    0.64
    辱
    0.64
    POSITIVE LOGITS
    japan
    0.84
     Rings
    0.82
     Schad
    0.81
     Ships
    0.80
     five
    0.80
     Scholarships
    0.80
     Japan
    0.78
     Seats
    0.78
     Ship
    0.77
     Materials
    0.77
    Activations Density 0.000%

    No Known Activations