© 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. 164656
    Prev
    Next
    INDEX
    Explanations

    analyzing text with foreign language characters

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

    pattern: following colon or asterisk

    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
    宽度
    0.48
    ndon
    0.46
     коюм
    0.45
     =)
    0.44
    能源
    0.44
    氦
    0.44
    elat
    0.44
    ancake
    0.43
    cam
    0.43
    ٨
    0.43
    POSITIVE LOGITS
    물
    0.61
    를
    0.56
    物
    0.55
    ಗೋ
    0.50
    いろ
    0.50
    용
    0.49
    워크
    0.47
    물을
    0.47
    형
    0.46
    ุป
    0.46
    Activations Density 0.000%

    No Known Activations