© 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. 40-GEMMASCOPE-2-RES-262K
    7. 215421
    Prev
    Next
    INDEX
    Explanations

    specifies the description

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     gi
    0.45
     apparel
    0.39
     gen
    0.38
     stream
    0.37
     fica
    0.37
     __
    0.37
     freestyle
    0.36
     rip
    0.36
     young
    0.36
     joins
    0.36
    POSITIVE LOGITS
    நாயகம்
    0.42
    Residual
    0.41
    Brexit
    0.40
    Science
    0.40
    丧
    0.39
    Diag
    0.38
    𝐁
    0.38
    Tabs
    0.38
    Chunks
    0.38
    GraphQl
    0.38
    Activations Density 0.000%

    No Known Activations