© 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. 4477
    Prev
    Next
    INDEX
    Explanations

    languages and linguistics

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

    Cantonese, Catalan, Arabic, German, Bengali, Khmer

    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
    淤
    0.28
     чином
    0.27
     এগিয়ে
    0.27
     кілька
    0.27
     nahezu
    0.27
     Wochenende
    0.26
     Якщо
    0.26
     גם
    0.25
     Київ
    0.25
     автомобі
    0.25
    POSITIVE LOGITS
    名は
    0.28
    佢
    0.27
     organisms
    0.26
     sexuality
    0.25
    দিগকে
    0.25
     scientists
    0.24
     organism
    0.24
     vertebrates
    0.24
    だよ
    0.24
     sects
    0.23
    Activations Density 0.059%

    No Known Activations