© 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. 51999
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by nouns

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

    majority Muslims,Qaeda, calls

    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
    生成
    0.50
     زاده
    0.50
    би
    0.50
    Atlantic
    0.49
    IDAD
    0.48
    лость
    0.48
    ט
    0.47
    一
    0.46
    ING
    0.46
    Alexandra
    0.45
    POSITIVE LOGITS
     अधिकांश
    0.53
     Sticker
    0.49
     बहुतेक
    0.48
     পদ্ধতি
    0.48
     সংখ্য
    0.47
     Wee
    0.45
     ಎಲ್ಲಾ
    0.45
     Vis
    0.45
     relig
    0.44
     निर्
    0.43
    Activations Density 0.000%

    No Known Activations