© 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. 159297
    Prev
    Next
    INDEX
    Explanations

    multilingual transition words

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

    manipulating symbols

    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
    由
    0.57
     menyimpan
    0.52
    如
    0.50
    是
    0.49
    ल्शियम
    0.49
     समुद्रा
    0.48
    เป็น
    0.46
     como
    0.46
     như
    0.45
     praia
    0.45
    POSITIVE LOGITS
     руководство
    0.48
     جناب
    0.47
     ಕಂಡ
    0.47
    wise
    0.46
     loy
    0.46
     ಘ
    0.44
     ગ્ર
    0.44
     მკ
    0.44
     odpowied
    0.44
    শি
    0.44
    Activations Density 0.000%

    No Known Activations