© 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. 16874
    Prev
    Next
    INDEX
    Explanations

    users navigate applications

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

    clarifying output and user experience

    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
    ALL
    0.44
    AND
    0.42
    שי
    0.39
    Equations
    0.38
    Xét
    0.38
     equations
    0.38
     BEING
    0.38
    Ꭹ
    0.37
    Loving
    0.37
    Statuses
    0.37
    POSITIVE LOGITS
     Bedien
    0.56
     صارفین
    0.52
     Öffentlichkeit
    0.49
     Benutzer
    0.48
     نمایش
    0.48
     Pfe
    0.47
     oczywiście
    0.47
     Verbesser
    0.47
     Bildschirm
    0.47
     kullanıcı
    0.46
    Activations Density 0.054%

    No Known Activations