© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144681
    Prev
    Next
    INDEX
    Explanations

    listing, sending, accepting

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

    text formats and languages

    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
     libid
    0.50
     hardcover
    0.49
    as
    0.47
    s
    0.47
     ebook
    0.45
    invalid
    0.45
     audiobook
    0.44
     eBook
    0.44
     dui
    0.44
     mmol
    0.43
    POSITIVE LOGITS
     gente
    0.53
    ارب
    0.48
    itaea
    0.48
    ينه
    0.46
     Inglaterra
    0.46
    نين
    0.46
    農
    0.46
    횽
    0.46
    꾿
    0.44
    휙
    0.44
    Activations Density 0.000%

    No Known Activations