© 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. 194090
    Prev
    Next
    INDEX
    Explanations

    foreign words, others, workers

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

    transactional intimacy and strategy

    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
     but
    0.46
     consented
    0.46
     bukti
    0.46
     dependant
    0.43
    ки
    0.42
    кою
    0.42
    Verified
    0.42
    뚝
    0.41
     venturing
    0.40
    슨
    0.40
    POSITIVE LOGITS
     ሌሎች
    0.50
     തൊഴിലാ
    0.50
     কর্মীদের
    0.49
     אחר
    0.47
     lavoratori
    0.47
     হোস্ট
    0.46
     পুলিশের
    0.46
     ተመሳሳይ
    0.46
     ശ
    0.45
     Coyote
    0.45
    Activations Density 0.001%

    No Known Activations