© 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. 206809
    Prev
    Next
    INDEX
    Explanations

    for practical

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

    architectural design and mobile games

    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
    思
    0.48
    対応
    0.47
     Pi
    0.46
    런
    0.45
     UR
    0.45
     편
    0.45
     Si
    0.43
     IL
    0.43
     Lago
    0.43
    接近
    0.43
    POSITIVE LOGITS
    ণ্ডে
    0.55
    rfc
    0.53
    uangan
    0.52
     cercare
    0.50
     myBuilder
    0.50
    Mitsubishi
    0.49
     দক্ষ
    0.49
    ريقيا
    0.48
     বাধ্যতামূলক
    0.48
     সেন
    0.46
    Activations Density 0.000%

    No Known Activations