© 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. 245083
    Prev
    Next
    INDEX
    Explanations

    language identification

    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
    kate
    0.49
    ᱔
    0.48
    可靠
    0.47
    dataSource
    0.46
    此类
    0.46
    $(\
    0.46
    nics
    0.46
    poruč
    0.45
    thal
    0.45
    ')
    0.45
    POSITIVE LOGITS
     filmu
    0.52
    ちゃんの
    0.49
     Сьогодні
    0.48
    。「
    0.47
     เมื่อ
    0.46
     영화
    0.46
     često
    0.46
     เริ่ม
    0.46
     welchen
    0.45
     ウ
    0.45
    Activations Density 0.001%

    No Known Activations