© 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. 228626
    Prev
    Next
    INDEX
    Explanations

    player,"Johnson",ships,potential,highest scores

    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
    #,
    0.49
     Egipto
    0.49
    includes
    0.45
     Москве
    0.45
    first
    0.44
    oscopy
    0.44
    fate
    0.44
    }${
    0.43
    fontenc
    0.43
    {};
    0.43
    POSITIVE LOGITS
     Rookie
    0.48
    运动员
    0.46
     প্রেসিডেন্টের
    0.45
    异
    0.45
    褪
    0.45
     Funny
    0.44
     फ्रंट
    0.43
     Transition
    0.43
     Freshman
    0.43
    进步
    0.43
    Activations Density 0.002%

    No Known Activations