© 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. 31-GEMMASCOPE-2-RES-262K
    7. 3085
    Prev
    Next
    INDEX
    Explanations

    relative price and percentage

    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/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    är
    0.45
     animals
    0.45
     लिख
    0.44
    0
    0.43
     anul
    0.42
    ë
    0.42
    l
    0.41
    y
    0.41
    lig
    0.41
    é
    0.39
    POSITIVE LOGITS
    Subscriptions
    0.50
     andRow
    0.48
    Avatar
    0.48
    ASER
    0.48
    Pricing
    0.47
     कृति
    0.47
    ល្អ
    0.47
     यूपीएससी
    0.46
    诸多
    0.46
    ಟಕ
    0.45
    Activations Density 0.000%

    No Known Activations