© 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. 197631
    Prev
    Next
    INDEX
    Explanations

    winning, shipping, indemnities

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

    Economic or as tools

    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
     Resistant
    0.48
     meydana
    0.47
    钟
    0.46
    బ్బు
    0.45
    蹩
    0.44
     Scottsdale
    0.44
     yaşayan
    0.43
     Bayou
    0.43
    塘
    0.43
     resistant
    0.43
    POSITIVE LOGITS
    ä
    0.58
    лка
    0.50
    for
    0.48
    부
    0.48
    from
    0.46
     instrumento
    0.46
     instrument
    0.46
    gf
    0.46
    as
    0.46
     filepath
    0.46
    Activations Density 0.000%

    No Known Activations