© 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. 169875
    Prev
    Next
    INDEX
    Explanations

    maintained at

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

    two apples

    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
    Привет
    0.54
    拶
    0.53
    Ни
    0.52
    Добрый
    0.52
    Прави
    0.50
    یت
    0.48
    ন
    0.48
    Рабо
    0.47
    Этот
    0.47
    ત
    0.46
    POSITIVE LOGITS
    比如說
    0.55
     안전
    0.48
     abstinence
    0.47
     ㅎㅎ
    0.46
     而且
    0.46
     constellations
    0.46
     moistened
    0.46
     אבל
    0.45
     花
    0.45
    flowers
    0.44
    Activations Density 0.001%

    No Known Activations