© 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. 13867
    Prev
    Next
    INDEX
    Explanations

    wide and broad concepts

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

    The main thing this neuron does is find technical references to radio-frequency bandwidths and spectrum (e.g. “wide band,” “band-limited,” “spectrum”).

    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
    ச்சின்ன
    0.63
    大型
    0.63
     geoLocation
    0.62
    ♘
    0.61
    Geolocation
    0.61
    ffic
    0.58
     coward
    0.57
    cupine
    0.57
    seo
    0.55
     निर्धारण
    0.55
    POSITIVE LOGITS
     широ
    1.20
     widths
    1.20
     širo
    1.19
     wide
    1.17
     Wide
    1.16
    Wide
    1.16
     Width
    1.15
    宽
    1.15
     Narrow
    1.13
    窄
    1.10
    Activations Density 0.171%

    No Known Activations