© 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. 126931
    Prev
    Next
    INDEX
    Explanations

    testing, governing, specific adjectives

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

    refusals or limitations

    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
     પોતા
    0.50
     Η
    0.49
    Weblinks
    0.49
     http
    0.49
     реєстра
    0.48
     erhält
    0.46
     βρίσκεται
    0.46
    ijski
    0.46
    httphttps
    0.46
    之时
    0.45
    POSITIVE LOGITS
     testers
    0.50
     incompet
    0.49
     fric
    0.48
     finit
    0.47
    頬
    0.46
    forgot
    0.46
    インド
    0.46
    AND
    0.45
     incompat
    0.44
    適
    0.44
    Activations Density 0.001%

    No Known Activations