© 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. 79212
    Prev
    Next
    INDEX
    Explanations

    web site security

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

    finding information and explanations

    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
    (
    0.56
    ((
    0.55
     LEVELS
    0.50
    ctuaries
    0.49
     Bridges
    0.48
    ridges
    0.48
     نظم
    0.47
     VStack
    0.46
    ([
    0.45
    (\
    0.45
    POSITIVE LOGITS
    જાર
    0.51
    "。
    0.49
    ीड
    0.47
     oligonucleotide
    0.46
    اديم
    0.46
    ौ
    0.46
    一部
    0.45
     accur
    0.45
     herhangi
    0.45
    lady
    0.44
    Activations Density 0.001%

    No Known Activations