© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 147702
    Prev
    Next
    INDEX
    Explanations

    popularity and prominence

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

    code and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Framing
    0.53
     IncludeField
    0.52
     postulated
    0.52
     \
    0.51
     Assumptions
    0.46
     processors
    0.46
     included
    0.45
     Calculation
    0.45
     decimals
    0.45
    ம்தா
    0.45
    POSITIVE LOGITS
    tem
    0.51
    ve
    0.45
    溪
    0.45
    ji
    0.44
    popularity
    0.44
    vem
    0.44
    sli
    0.44
     సంఘ
    0.44
    tz
    0.44
    fler
    0.44
    Activations Density 0.000%

    No Known Activations