© 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. 5002
    Prev
    Next
    INDEX
    Explanations

    following "Pictures/" or "Args:"

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

    The neuron flags filesystem‐style path components—directory and file names (and their separators) in URLs or file system paths.

    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
    plugin
    0.59
    outil
    0.59
    তথ্য
    0.58
    phil
    0.57
    rophot
    0.56
    栻
    0.56
     পরীক্ষা
    0.55
    disamb
    0.55
    訌
    0.55
    이제
    0.54
    POSITIVE LOGITS
     ù
    0.73
     Reyes
    0.64
     ¡
    0.62
     Και
    0.62
     ৯
    0.61
     Andrey
    0.61
     da
    0.61
     Agustus
    0.61
     Agnes
    0.61
     Jake
    0.60
    Activations Density 0.031%

    No Known Activations