© 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. 188768
    Prev
    Next
    INDEX
    Explanations

    requests for service

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

    nacido de

    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
     perennials
    0.46
    าระ
    0.46
     ponds
    0.46
     crucible
    0.44
    ikä
    0.43
     рік
    0.42
    لاث
    0.41
    <0x97>
    0.40
    нические
    0.40
    ляр
    0.40
    POSITIVE LOGITS
    =>
    0.55
    versation
    0.47
     عندنا
    0.46
     আদর
    0.45
    CEST
    0.45
     CBC
    0.45
     তাছাড়া
    0.43
     abz
    0.43
     medias
    0.43
    cpf
    0.43
    Activations Density 0.001%

    No Known Activations