© 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. 252346
    Prev
    Next
    INDEX
    Explanations

    chapter in, site, future beh, way for

    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
    욀
    0.54
    вающей
    0.52
    Щ
    0.49
    翱
    0.48
    нием
    0.47
    еве
    0.45
    userAgent
    0.45
    вши
    0.44
    ਾਰੇ
    0.44
     regrettable
    0.44
    POSITIVE LOGITS
    s
    0.49
     Styles
    0.46
     Institute
    0.45
     Ij
    0.45
     Rath
    0.44
     Tap
    0.43
     Sekolah
    0.42
     Malaga
    0.42
     Top
    0.42
    op
    0.42
    Activations Density 0.000%

    No Known Activations