© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7966
    Prev
    Next
    INDEX
    Explanations

    if __name__ == "__main__":

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Advantage
    0.61
     advantageous
    0.56
     Best
    0.55
     assassinated
    0.55
     Well
    0.54
    BEST
    0.53
     advantage
    0.52
    ì
    0.52
     Toxicity
    0.52
     Life
    0.51
    POSITIVE LOGITS
     :=\
    0.66
    NotExist
    0.62
    снов
    0.62
    $=\
    0.61
    ensical
    0.61
     utilice
    0.60
    breviations
    0.60
     $=\
    0.59
    RootDir
    0.57
    :=\
    0.57
    Activations Density 0.002%

    No Known Activations