© 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. 98649
    Prev
    Next
    INDEX
    Explanations

    recipe instructions with measurements

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

    actions requiring description

    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
    ق
    0.50
    áč
    0.49
    ب
    0.49
    بق
    0.46
    كان
    0.45
    starred
    0.45
    طب
    0.44
    فيق
    0.44
    空港
    0.44
    愁
    0.44
    POSITIVE LOGITS
    +',
    0.44
     স্টি
    0.43
     ENGINE
    0.42
     समझना
    0.42
     asegurarse
    0.41
    +')
    0.41
     Unified
    0.40
     hand
    0.40
     नाज
    0.40
    ^{-\
    0.39
    Activations Density 0.003%

    No Known Activations