© 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. 5003
    Prev
    Next
    INDEX
    Explanations

    friendly

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     december
    0.73
     november
    0.66
     květ
    0.64
     september
    0.61
     ligt
    0.61
     february
    0.61
     [.
    0.61
     uk
    0.61
     germany
    0.61
     tuesday
    0.61
    POSITIVE LOGITS
     alluded
    0.64
    िसोदिया
    0.60
    дир
    0.60
     Ecc
    0.57
     Од
    0.55
     провин
    0.55
    ᆻ
    0.54
     Кан
    0.54
     noteworthy
    0.54
     peculiarity
    0.52
    Activations Density 0.225%

    No Known Activations