© 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. 86316
    Prev
    Next
    INDEX
    Explanations

    unless agreedIs Toobe years

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

    common approaches and strategies

    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
    諷
    0.46
     願い
    0.46
     अधिकारियों
    0.46
    惱
    0.45
    อัต
    0.44
     भाई
    0.43
    บุคคล
    0.43
     বিরাজ
    0.42
     編
    0.42
     oamenii
    0.42
    POSITIVE LOGITS
     winch
    0.55
     integro
    0.54
    ßer
    0.50
     mong
    0.49
     zatim
    0.47
    iteur
    0.46
    zhu
    0.45
    oram
    0.43
    وتا
    0.42
    жаю
    0.41
    Activations Density 0.000%

    No Known Activations