© 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. 11017
    Prev
    Next
    INDEX
    Explanations

    language codes in urls

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

    English language code

    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
    ূত
    0.49
    狐
    0.48
    垛
    0.46
    ভাসের
    0.46
    㡱
    0.46
    ProductRunnable
    0.45
     Bxf
    0.45
    芓
    0.45
    ऊंगी
    0.44
    asena
    0.43
    POSITIVE LOGITS
    wikipedia
    0.53
    language
    0.51
     translation
    0.49
    wiki
    0.48
     anglais
    0.48
     language
    0.48
    sprach
    0.47
     english
    0.47
     анг
    0.47
     انگلیسی
    0.47
    Activations Density 0.008%

    No Known Activations