© 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. 19991
    Prev
    Next
    INDEX
    Explanations

    foreign scripts

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

    Slavic names

    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
    ></
    0.06
     there
    0.06
     там
    0.05
    ;
    0.05
     won
    0.05
     -
    0.05
     Цена
    0.05
     haven
    0.05
     ©
    0.05
     —
    0.05
    POSITIVE LOGITS
    オ
    0.06
    ویں
    0.05
    োম
    0.05
    咆
    0.05
    見る
    0.05
    スト
    0.05
    ز
    0.05
    ⺆
    0.05
    行く
    0.05
    ಗ್
    0.05
    Activations Density 0.000%

    No Known Activations