© 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. 197277
    Prev
    Next
    INDEX
    Explanations

    letter t preschool

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

    explaining conditions and requirements

    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
     фестива
    0.55
    señ
    0.49
    等を
    0.48
    ñ
    0.46
    ெல்ல
    0.45
     чему
    0.45
    हाना
    0.45
     Winters
    0.44
     Espan
    0.44
     Spaniard
    0.44
    POSITIVE LOGITS
     yakni
    0.42
    เพื่อให้
    0.42
    namely
    0.42
    刓
    0.40
     orientation
    0.39
     yaitu
    0.39
    ‌ترین
    0.38
    iled
    0.37
    ّة
    0.37
     اکاؤنٹ
    0.37
    Activations Density 0.001%

    No Known Activations