© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 99402
    Prev
    Next
    INDEX
    Explanations

    tree resin and related sticky substances

    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
    Not in Any Lists

    No Comments

    Negative Logits
     dimensionless
    0.48
     배열
    0.43
    丰
    0.41
     ഭക്ഷണം
    0.40
     समाय
    0.40
    节能
    0.40
     పాఠ
    0.39
    任
    0.38
    片
    0.38
    娣
    0.38
    POSITIVE LOGITS
     gum
    0.67
     tincture
    0.64
     exud
    0.63
     Gum
    0.59
     tinct
    0.58
     tartar
    0.57
    Gum
    0.57
     glue
    0.56
     Glue
    0.55
     gums
    0.55
    Activations Density 0.009%

    No Known Activations