© 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. 237018
    Prev
    Next
    INDEX
    Explanations

    business consequence

    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
     و
    0.79
     وبا
    0.64
     ও
    0.62
     и
    0.61
     وم
    0.59
     व
    0.58
     ک
    0.55
     và
    0.55
     ו
    0.55
     și
    0.54
    POSITIVE LOGITS
    ழுகு
    0.45
     bushels
    0.43
    essayer
    0.43
    ರ್ಷ
    0.43
    OUTPUT
    0.43
     desserts
    0.43
    Medico
    0.43
     waterfowl
    0.43
    Entrepreneur
    0.42
     každý
    0.42
    Activations Density 0.000%

    No Known Activations