© 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. 50434
    Prev
    Next
    INDEX
    Explanations

    words from multiple languages

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

    artificial intelligence

    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
    творе
    0.55
     ہو۔
    0.47
    顿时
    0.45
    夊
    0.43
     suspiciously
    0.43
     کافی
    0.42
     გამ
    0.42
    䚲
    0.42
     tantôt
    0.42
     المست
    0.42
    POSITIVE LOGITS
     revolución
    0.46
     apellidos
    0.41
     merupakan
    0.41
     museums
    0.41
     Revolución
    0.40
     Dünya
    0.40
     cemeteries
    0.40
     próxima
    0.40
     जाएंगे
    0.40
    aterials
    0.40
    Activations Density 0.000%

    No Known Activations