© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 116008
    Prev
    Next
    INDEX
    Explanations

    opening or closing statements

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

    oxygen, health, healing

    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
     Arrivals
    0.49
     NavBar
    0.48
     PRICES
    0.47
     inhuman
    0.47
     Microbiology
    0.47
     Ι
    0.46
     उसी
    0.46
     ০৯
    0.46
     Эти
    0.46
    ऊंगी
    0.46
    POSITIVE LOGITS
    шире
    0.54
     conteúdo
    0.52
     ٿ
    0.50
    協助
    0.50
     موس
    0.49
     resolução
    0.47
    ด้าน
    0.47
    وس
    0.46
     perda
    0.45
    歡迎
    0.44
    Activations Density 0.001%

    No Known Activations