© 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. 203826
    Prev
    Next
    INDEX
    Explanations

    legal limits and charges

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

    performance issues

    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
    נן
    0.43
    当日
    0.42
    ता
    0.39
    ニア
    0.39
    那天
    0.38
    હ
    0.38
     champion
    0.37
     offseason
    0.37
     summers
    0.37
     breakthroughs
    0.37
    POSITIVE LOGITS
    addWidget
    0.54
    QWidget
    0.52
     İstifadə
    0.47
    Framebuffer
    0.47
     Agriculture
    0.46
    嗔
    0.46
    colorPrimary
    0.46
    ید
    0.46
     Controller
    0.46
     Irrigation
    0.46
    Activations Density 0.000%

    No Known Activations