© 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. 26672
    Prev
    Next
    INDEX
    Explanations

    foreign characters and diverse languages

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

    helper functions and time updates

    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
     Adriatic
    0.60
     Advent
    0.51
     Sumatra
    0.51
     carnage
    0.50
     Levante
    0.49
     a
    0.47
     Aś
    0.46
     Lebanon
    0.46
     Apex
    0.46
     astronom
    0.46
    POSITIVE LOGITS
     ඇ
    0.48
    ILLE
    0.44
     علی
    0.43
    yse
    0.43
     участие
    0.43
    STE
    0.43
     ሂደት
    0.43
    Pat
    0.43
    ELD
    0.42
    chtigt
    0.42
    Activations Density 0.000%

    No Known Activations