© 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. 4978
    Prev
    Next
    INDEX
    Explanations

    guardians of

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

    The neuron fires on words that appear in document “headers” or titles—especially email subject‐line tokens (e.g. “Re:,” “Online,” “account,” “information,” etc.).

    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
     Chứng
    0.47
    笫
    0.45
    <unused56>
    0.45
     Đến
    0.43
     ভারতবর্ষে
    0.43
     Kuv
    0.42
     நுரையீரல்
    0.42
     Moistur
    0.42
    荽
    0.42
     って
    0.42
    POSITIVE LOGITS
     &
    0.43
    Â
    0.40
     without
    0.40
    /
    0.39
    <unused63>
    0.38
    <unused60>
    0.37
     bertahan
    0.36
    <unused62>
    0.35
    &
    0.35
    …
    0.35
    Activations Density 0.356%

    No Known Activations