© 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. 41949
    Prev
    Next
    INDEX
    Explanations

    et al

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

    French language, questions

    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
     ке
    0.62
     цикла
    0.59
     модуля
    0.59
     цик
    0.59
     конденса
    0.57
     спект
    0.57
     типа
    0.56
     규
    0.55
     konstruk
    0.55
     бур
    0.55
    POSITIVE LOGITS
     déf
    0.78
     deux
    0.75
     référence
    0.71
    èces
    0.70
    afficher
    0.70
     où
    0.70
     présente
    0.70
     poids
    0.70
     frère
    0.70
     entièrement
    0.69
    Activations Density 0.018%

    No Known Activations