© 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. 74878
    Prev
    Next
    INDEX
    Explanations

    country codes and names

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

    bets and feedback

    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
    Έ
    0.49
    FRONT
    0.49
    У
    0.47
    ABILITIES
    0.45
    เป็น
    0.43
     உங்களுக்கு
    0.43
    STEIN
    0.43
    أن
    0.42
    και
    0.42
    تنا
    0.41
    POSITIVE LOGITS
    变革
    0.48
     malay
    0.47
    icules
    0.46
     တို့
    0.46
    aree
    0.46
     オレンジ
    0.45
     草
    0.45
     आया
    0.43
     مصرى
    0.43
     démarrage
    0.43
    Activations Density 0.000%

    No Known Activations