© 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. 74808
    Prev
    Next
    INDEX
    Explanations

    guards livestock

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

    safety and security regulations

    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
    бор
    0.49
    У
    0.49
    hilt
    0.49
    氨
    0.46
    버스
    0.45
    نك
    0.45
    פון
    0.44
     सूखे
    0.44
    电脑
    0.43
    Боль
    0.43
    POSITIVE LOGITS
     ਭ
    0.45
     معی
    0.44
     PUBL
    0.42
     ভাস
    0.42
     প্রকাশের
    0.41
     ಸ್ಥಾನ
    0.41
     पहुँचा
    0.41
     উচ্চার
    0.41
     чувства
    0.41
     pathogenesis
    0.40
    Activations Density 0.000%

    No Known Activations