© 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. 42792
    Prev
    Next
    INDEX
    Explanations

    information in multiple languages

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

    starting punctuation

    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
    льном
    0.52
     tujuh
    0.49
    fromParams
    0.48
     Гульнявыя
    0.48
    欧
    0.48
    нул
    0.47
    ᱝ
    0.45
     অভিনে
    0.45
    ಿಯನ್
    0.45
    शियल
    0.44
    POSITIVE LOGITS
     informazioni
    0.49
     eventuali
    0.46
     information
    0.45
     سؤال
    0.44
     Informationen
    0.43
     This
    0.43
     “
    0.43
     केवल
    0.43
     وهذا
    0.42
     neither
    0.42
    Activations Density 0.000%

    No Known Activations