© 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. 31688
    Prev
    Next
    INDEX
    Explanations

    foreign or archaic words

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

    languages, or technical terms

    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
     donuts
    0.49
    哈
    0.49
     completes
    0.47
    ب
    0.47
     Donuts
    0.47
     Jar
    0.44
     Chees
    0.43
     tees
    0.43
     artigos
    0.43
    Ş
    0.43
    POSITIVE LOGITS
     kanilang
    0.47
     треба
    0.47
     serviceable
    0.46
     tjen
    0.44
     выражение
    0.44
     반드시
    0.43
     arbete
    0.43
     ಇದ್ದ
    0.42
     року
    0.42
     saith
    0.42
    Activations Density 0.000%

    No Known Activations