© 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. 109784
    Prev
    Next
    INDEX
    Explanations

    handling foreign characters

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

    depends on how

    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
     artístico
    0.47
     অষ্টম
    0.45
     männ
    0.44
     cellulaire
    0.44
     細胞
    0.44
     harán
    0.44
    াচিত
    0.43
    =@@
    0.43
     değerli
    0.43
     লেখকের
    0.43
    POSITIVE LOGITS
    нете
    0.56
    в
    0.52
     civilians
    0.48
    Ха
    0.48
    Само
    0.47
    ฝ
    0.47
    В
    0.45
    ໂຕ
    0.44
    род
    0.44
     Роди
    0.43
    Activations Density 0.001%

    No Known Activations