© 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. 46246
    Prev
    Next
    INDEX
    Explanations

    arrested, detained, accused

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

    actions against accused individuals

    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
    法语
    0.43
    leşik
    0.42
    竞赛
    0.41
     katika
    0.40
     कहानियां
    0.40
    灿
    0.40
     انگل
    0.40
    ستر
    0.39
     sillons
    0.39
    栎
    0.39
    POSITIVE LOGITS
     accused
    0.76
     individuals
    0.75
     आरोपियों
    0.72
     arrested
    0.72
     indicted
    0.71
     arrests
    0.67
    individuals
    0.67
     গ্রেফতার
    0.65
     perpetrators
    0.65
     suspects
    0.64
    Activations Density 0.074%

    No Known Activations