© 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. 120115
    Prev
    Next
    INDEX
    Explanations

    specific topics and their follow-ups

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

    preventing facial disfigurement or halos

    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
    🄰
    0.54
    ่าย
    0.49
    щено
    0.49
    広い
    0.48
    ikovsky
    0.48
    太
    0.45
    受到了
    0.45
    片
    0.45
    अधिका
    0.45
    ังหวัด
    0.45
    POSITIVE LOGITS
     posteriorly
    0.48
    list
    0.45
     Jeżeli
    0.43
     succumb
    0.43
    jap
    0.43
    ień
    0.42
     قائمة
    0.41
     aufgebaut
    0.41
    ())
    0.41
     blushing
    0.40
    Activations Density 0.001%

    No Known Activations