© 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. 12818
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    Not in Any Lists

    No Comments

    Negative Logits
     rosem
    0.47
     handkerchief
    0.47
    ἓ
    0.46
     meandering
    0.45
     denitrification
    0.45
    壹章
    0.45
    ){//
    0.44
     sediment
    0.43
     vineyard
    0.43
     sprayer
    0.43
    POSITIVE LOGITS
    if
    0.58
    StringBuilder
    0.58
    Anonymous
    0.56
    Android
    0.55
    S
    0.50
     Anonymous
    0.48
    ((
    0.47
    Int
    0.46
    Object
    0.45
    Class
    0.45
    Activations Density 0.000%

    No Known Activations