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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 84683
    Prev
    Next
    INDEX
    Explanations

    per socket, per block, per page

    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
    婄
    0.46
    每一個
    0.43
     계약
    0.41
     każde
    0.40
    轎
    0.40
    aban
    0.40
     everytime
    0.40
    eventId
    0.39
     каж
    0.39
     ofert
    0.39
    POSITIVE LOGITS
     చూప
    0.39
    rophe
    0.38
     Review
    0.38
     Worker
    0.38
     Geophys
    0.37
    uct
    0.37
     guad
    0.37
     somewhat
    0.36
    骤
    0.36
     हेव
    0.35
    Activations Density 0.005%

    No Known Activations