Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 190
    Prev
    Next
    INDEX
    Explanations

    law enforcement and violations

    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_16_width_16k_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
    و
    0.48
    ના
    0.47
    ные
    0.46
    ல்
    0.43
    thedocs
    0.43
    ра
    0.42
    hive
    0.42
    ных
    0.42
     Á
    0.40
     Pittsburg
    0.40
    POSITIVE LOGITS
     offenders
    0.45
     policiais
    0.45
     offences
    0.42
     полицей
    0.41
     homic
    0.41
     delitos
    0.39
     violators
    0.39
    ตำรวจ
    0.38
     polici
    0.38
     enforcement
    0.38
    Activations Density 2.145%

    No Known Activations