© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 170343
    Prev
    Next
    INDEX
    Explanations

    cosmic voyager

    np_acts-logits-general · gemini-2.5-flash-lite

    filler conversational language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     удаления
    0.45
    верх
    0.45
    czna
    0.43
    m
    0.43
     должности
    0.43
    шает
    0.42
    noe
    0.42
    χος
    0.42
    gF
    0.42
    ylation
    0.42
    POSITIVE LOGITS
    囑
    0.48
     cumpl
    0.43
    gridView
    0.43
    တွ
    0.43
     mitt
    0.43
     metall
    0.42
    दरी
    0.42
     merchand
    0.42
    accoon
    0.41
    с
    0.41
    Activations Density 0.002%

    No Known Activations