© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 11370
    Prev
    Next
    INDEX
    Explanations

    function start/end with discard None

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    น์
    0.53
    Drain
    0.45
    варти
    0.45
    萂
    0.44
    Kota
    0.43
    ﻥ
    0.43
     আমিন
    0.43
     यांची
    0.43
    㢦
    0.43
    Amount
    0.42
    POSITIVE LOGITS
     ticketing
    0.40
     Bridget
    0.39
     Unilever
    0.39
    le
    0.39
    uen
    0.38
    getCharAt
    0.38
     Ticket
    0.38
     அழிக்க
    0.38
     tide
    0.38
     Tickets
    0.38
    Activations Density 3.171%

    No Known Activations