© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 9437
    Prev
    Next
    INDEX
    Explanations

    jQuery, Python, Stormlight, wind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    indication
    0.42
    characteristic
    0.39
    лета
    0.38
    titanic
    0.38
    hydroxyl
    0.38
    linestyle
    0.38
    dwelling
    0.37
    lex
    0.37
    ⓘ
    0.37
    يان
    0.37
    POSITIVE LOGITS
     UV
    0.58
     uv
    0.52
    UV
    0.48
     Complet
    0.46
    uv
    0.42
     ultraviolet
    0.42
     Ultraviolet
    0.40
     completions
    0.40
    Rud
    0.40
    uvi
    0.39
    Activations Density 0.002%

    No Known Activations