© 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. 191047
    Prev
    Next
    INDEX
    Explanations

    adding or replacing parts

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

    neural network errors and time series

    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
     .
    0.54
    .
    0.52
    ).
    0.48
    !.
    0.46
     two
    0.45
    !
    0.45
     would
    0.44
     religiously
    0.44
     roster
    0.44
     because
    0.43
    POSITIVE LOGITS
    ículas
    0.50
    malloc
    0.47
     emberek
    0.47
     కంప
    0.46
    prix
    0.46
    {}\
    0.45
     రూప
    0.45
     პროგრამ
    0.45
    Prix
    0.45
     ხელისუფ
    0.44
    Activations Density 0.001%

    No Known Activations