© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 99168
    Prev
    Next
    INDEX
    Explanations

    scientific citations and identifiers

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

    products, sum, new, prime

    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
     breadth
    0.50
     disappoint
    0.47
     vue
    0.46
     broaden
    0.45
     straighten
    0.45
    闻
    0.45
    辩
    0.45
    رف
    0.44
     broadest
    0.44
     PRACT
    0.44
    POSITIVE LOGITS
    prestations
    0.55
    Quota
    0.54
    akk
    0.52
    otrop
    0.50
    adion
    0.49
    eltat
    0.49
    irts
    0.48
    gettags
    0.48
    WhiteRatingDiff
    0.47
    values
    0.47
    Activations Density 0.000%

    No Known Activations