© 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. 161992
    Prev
    Next
    INDEX
    Explanations

    notify owners of recalls

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

    returning home today

    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
     ouv
    0.52
     •
    0.47
     œ
    0.46
     cha
    0.46
     carre
    0.46
     कूद
    0.45
     m
    0.44
     Cha
    0.44
     oan
    0.43
    •
    0.43
    POSITIVE LOGITS
    طلا
    0.46
    தமிழ
    0.46
    erweise
    0.46
    EndDate
    0.46
    ними
    0.46
    تمل
    0.46
    ಿಸಿದೆ
    0.45
    ં
    0.45
    เริ่ม
    0.45
    كلات
    0.45
    Activations Density 0.001%

    No Known Activations