© 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. 4932
    Prev
    Next
    INDEX
    Explanations

    horizontal and vertical dimensions

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

    The neuron activates on numeric measurements and quantity expressions (e.g. dimensions, counts, spacing metrics).

    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_31_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
     instytuc
    0.61
     pulang
    0.60
     desblo
    0.60
     féri
    0.59
     достой
    0.59
     amber
    0.57
     žal
    0.57
     öpp
    0.57
    <unused635>
    0.57
     repatriation
    0.56
    POSITIVE LOGITS
     पीरियड
    0.58
    射线
    0.58
    巉
    0.58
    垂直
    0.57
     Horizontal
    0.57
    ヒト
    0.57
    呲
    0.56
    横
    0.56
    ր
    0.55
    反射
    0.54
    Activations Density 0.006%

    No Known Activations