© 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. 73883
    Prev
    Next
    INDEX
    Explanations

    local branches

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

    today's dates

    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
    ضل
    0.43
    担当
    0.42
     Translator
    0.39
    സ്ത്ര
    0.39
    чан
    0.39
    大
    0.39
    เก็บ
    0.38
    Lastly
    0.38
    ర్భ
    0.38
    嶇
    0.38
    POSITIVE LOGITS
     oggi
    0.54
     hoje
    0.51
     aujourd
    0.50
    𝓈
    0.50
     σήμερα
    0.49
     encouraged
    0.48
     cared
    0.48
     estación
    0.48
     bugün
    0.47
     önemlidir
    0.47
    Activations Density 0.000%

    No Known Activations