© 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. 210846
    Prev
    Next
    INDEX
    Explanations

    multilingual

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

    words in context of purpose or description

    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
     সার
    0.49
     matching
    0.45
    ’
    0.45
     rectangles
    0.44
     rules
    0.44
     preserves
    0.44
     supported
    0.43
     sovereign
    0.42
     guaranty
    0.42
     storefront
    0.42
    POSITIVE LOGITS
    attaque
    0.50
     프로그램을
    0.50
     निराशा
    0.48
    들을
    0.48
    Setelah
    0.48
     lentamente
    0.48
    踉
    0.47
    Introduceti
    0.47
    Terror
    0.47
    वेलकम
    0.46
    Activations Density 0.001%

    No Known Activations