© 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. 9036
    Prev
    Next
    INDEX
    Explanations

    identifiers and their values

    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
    Not in Any Lists

    No Comments

    Negative Logits
    >∕
    0.32
     polypes
    0.30
    CUSSION
    0.29
     músculos
    0.29
    Jeśli
    0.29
    ObjectTemp
    0.29
    基督
    0.29
    WallArray
    0.28
    VSLU
    0.28
     ऑक्साइड
    0.28
    POSITIVE LOGITS
     (
    0.45
    ,
    0.41
     =
    0.39
     was
    0.35
    ↵
    0.35
     Public
    0.34
        
    0.34
     The
    0.33
    .
    0.33
     It
    0.33
    Activations Density 0.287%

    No Known Activations