© 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. 100459
    Prev
    Next
    INDEX
    Explanations

    best price and promotions

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

    programming types and code structure

    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
    టమి
    0.47
    angers
    0.47
    лове
    0.44
    郘
    0.44
     سپاه
    0.43
    ኛው
    0.43
     കേരള
    0.43
    ън
    0.43
    ण्ड
    0.42
    aceous
    0.42
    POSITIVE LOGITS
     আল
    0.43
     enjo
    0.40
     признаки
    0.39
     vimos
    0.38
     криптовалю
    0.38
     injunctive
    0.38
    此同时
    0.37
     e
    0.37
     Along
    0.37
    Spotify
    0.37
    Activations Density 0.001%

    No Known Activations