© 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. 219255
    Prev
    Next
    INDEX
    Explanations

    numbers, ritual, smuggling, borders

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

    translation, daily, recipe

    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
    czas
    0.47
    价格
    0.46
    owią
    0.45
    报价
    0.45
    쨌
    0.45
    sv
    0.44
    资料
    0.43
    (**
    0.43
    全局
    0.43
    XII
    0.43
    POSITIVE LOGITS
     সীমান্তবর্তী
    0.48
     gamanam
    0.41
     ત્યારબાદ
    0.40
     abuso
    0.39
     tumorigen
    0.39
     dioses
    0.39
     rumores
    0.39
     smuggling
    0.38
     arsenic
    0.38
     intraper
    0.38
    Activations Density 0.002%

    No Known Activations