© 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. 86199
    Prev
    Next
    INDEX
    Explanations

    posted dates

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

    research and study findings

    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
     اغلب
    0.44
     روب
    0.44
     Betracht
    0.43
     وحده
    0.43
    ObjectUnderTest
    0.43
     خانه
    0.42
     fréquente
    0.41
    뻗
    0.41
     clenched
    0.40
     الوحده
    0.40
    POSITIVE LOGITS
    गैर
    0.52
     brewers
    0.52
     城
    0.50
     島
    0.48
     সকলে
    0.48
     tax
    0.47
    無し
    0.44
    人々
    0.44
     titers
    0.44
     Trade
    0.44
    Activations Density 0.001%

    No Known Activations