© 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. 146046
    Prev
    Next
    INDEX
    Explanations

    foreign language identifiers

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

    lists, explanations, citations

    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
    कियों
    0.49
    k
    0.49
    autoplay
    0.49
    Austin
    0.48
    logo
    0.48
    ﻱ
    0.46
    ARCHITECTURE
    0.46
    岷
    0.46
    border
    0.45
    fans
    0.45
    POSITIVE LOGITS
    otec
    0.54
     месяцев
    0.50
     semaines
    0.48
     महीनों
    0.46
     meminta
    0.46
     câteva
    0.45
    রূপ
    0.44
     струк
    0.43
    onyl
    0.43
    utada
    0.43
    Activations Density 0.001%

    No Known Activations