© 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. 5914
    Prev
    Next
    INDEX
    Explanations

    real official formal

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

    formal communication style

    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
     \
    0.33
     সর্বাধিক
    0.30
     Diese
    0.29
     TextField
    0.28
     基本
    0.28
     ,"
    0.28
     ,,
    0.28
     ofthe
    0.27
     সমু
    0.27
     Closeup
    0.27
    POSITIVE LOGITS
     رسمی
    0.30
    真实的
    0.29
    й
    0.28
     полноцен
    0.28
     সত্যিকারের
    0.26
     echte
    0.26
     profesional
    0.25
    ised
    0.25
    真正的
    0.25
    лдуу
    0.25
    Activations Density 0.500%

    No Known Activations