© 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. 250007
    Prev
    Next
    INDEX
    Explanations

    IEEE followed by conference or journal terms

    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
    Negative Logits
    ."',
    0.59
     résult
    0.57
     BANG
    0.57
    ꫝ
    0.55
    ﮭ
    0.55
    нија
    0.54
    خدام
    0.54
    ﭥ
    0.54
     всіх
    0.53
     yc
    0.53
    POSITIVE LOGITS
    an
    0.94
    The
    0.69
    on
    0.69
     has
    0.67
    I
    0.64
    ان
    0.62
    可以说
    0.61
    AB
    0.60
    O
    0.60
    X
    0.59
    Activations Density 0.001%

    No Known Activations