© 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. 31-GEMMASCOPE-2-RES-262K
    7. 124077
    Prev
    Next
    INDEX
    Explanations

    profile, record, wave, overall

    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_31_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
    iw
    0.47
    +{
    0.47
     Holidays
    0.47
    bbing
    0.47
    ič
    0.47
    ?’
    0.46
    തിരെ
    0.46
    डीसी
    0.46
     Around
    0.45
    junk
    0.44
    POSITIVE LOGITS
    。
    0.55
    лювання
    0.50
     sudoku
    0.45
     microstructure
    0.45
     topl
    0.44
     recalcul
    0.44
    蔵
    0.43
     cache
    0.43
     stockage
    0.43
     fattori
    0.42
    Activations Density 0.001%

    No Known Activations