© 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. 30346
    Prev
    Next
    INDEX
    Explanations

    engineering, manufacturing, and quality

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

    largest sovereign

    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
    报错
    0.51
    👶
    0.48
    🧚
    0.47
     پرومو
    0.47
    身份证
    0.46
    🧒
    0.46
     باتیں
    0.46
     অবতার
    0.45
    绑
    0.44
    会对
    0.44
    POSITIVE LOGITS
    常に
    0.59
     our
    0.55
     machining
    0.54
     welding
    0.54
     uncompromising
    0.54
     প্রকৌশ
    0.53
     geotechnical
    0.52
     unsurpassed
    0.51
     manufacturing
    0.50
     reliability
    0.50
    Activations Density 0.000%

    No Known Activations