© 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. 129813
    Prev
    Next
    INDEX
    Explanations

    Secondly, growth, work, vital

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

    historical context and biological facts

    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
    Negative Logits
     Maje
    0.45
    ンプ
    0.41
    xmax
    0.40
    xmin
    0.40
    xd
    0.40
    ६
    0.40
    day
    0.40
     ਹੈ
    0.40
     메뉴
    0.40
    xg
    0.40
    POSITIVE LOGITS
     engulfed
    0.49
    assertInstanceOf
    0.45
    impse
    0.43
     penned
    0.43
     engulf
    0.41
     IPO
    0.41
    或
    0.41
    лекет
    0.40
    或者
    0.40
     immersion
    0.40
    Activations Density 0.001%

    No Known Activations