© 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. 71378
    Prev
    Next
    INDEX
    Explanations

    taxable income and distributions

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

    code examples and explanations

    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
    你有
    0.49
    、
    0.47
     inicio
    0.46
    如果你
    0.44
    hase
    0.44
    ೇ
    0.44
     ooit
    0.43
    𝓙
    0.43
    messages
    0.43
    你要
    0.42
    POSITIVE LOGITS
     wypad
    0.46
     inaccur
    0.45
     сты
    0.44
    adır
    0.43
     پڑھی
    0.43
     இவ்வாறு
    0.40
     unfairly
    0.40
     लड़ा
    0.40
     inadequate
    0.39
     unduly
    0.39
    Activations Density 0.001%

    No Known Activations