© 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. 231245
    Prev
    Next
    INDEX
    Explanations

    foreign characters and 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
     máme
    0.51
     mají
    0.50
     deaktiv
    0.46
     manglid
    0.45
     majú
    0.44
    })$;
    0.44
     நீண்ட
    0.43
    実装
    0.43
     wody
    0.43
     sicht
    0.43
    POSITIVE LOGITS
    omination
    0.43
    ¬
    0.43
    ρα
    0.40
    ει
    0.39
     Granville
    0.39
     Saint
    0.39
     রাষ্ট্র
    0.39
     แสดง
    0.38
     Masonic
    0.38
    ق
    0.38
    Activations Density 0.001%

    No Known Activations