© 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. 154624
    Prev
    Next
    INDEX
    Explanations

    For introducing reason

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

    For God

    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
     γιατί
    0.40
     OPERATIONS
    0.38
    颏
    0.38
    jaty
    0.37
     lesquelles
    0.37
    😌
    0.37
    Sor
    0.37
    Leffler
    0.36
    瀨
    0.36
     एक्सरसा
    0.36
    POSITIVE LOGITS
     sake
    0.46
     سنگ
    0.41
    感到
    0.38
     রয়েছেন
    0.37
    ently
    0.36
     spoonful
    0.36
    engers
    0.35
     Sake
    0.34
     vannak
    0.34
     ول
    0.33
    Activations Density 0.025%

    No Known Activations