© 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. 105485
    Prev
    Next
    INDEX
    Explanations

    company has grown

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

    heritage and humanity

    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
     باشگاه
    0.50
    گز
    0.48
    ள்ளனர்
    0.47
     등이
    0.47
     debido
    0.46
    며
    0.46
     ponies
    0.44
    compatible
    0.44
     آن‌ها
    0.43
    ட்
    0.43
    POSITIVE LOGITS
     conspiracies
    0.49
     loosen
    0.47
    ULTS
    0.47
    រ
    0.46
     نوا
    0.45
     Directories
    0.45
     المن
    0.44
     със
    0.44
     eternally
    0.44
     সান্ত
    0.44
    Activations Density 0.000%

    No Known Activations