© 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. 45631
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, and specific items

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

    trend, disks, sing, nausea, risk, requests, craft

    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
     člen
    0.45
     పొ
    0.43
     উঠ
    0.42
     प्रमुख
    0.41
    โ
    0.41
     소재
    0.41
     आवासीय
    0.41
    ⏩
    0.41
     кў
    0.40
     डिटेल
    0.39
    POSITIVE LOGITS
     これは
    0.51
     Bauer
    0.42
     Jet
    0.42
     هذا
    0.41
     acol
    0.41
     kli
    0.40
    责任
    0.39
     numerals
    0.39
     acclimat
    0.39
     Voyages
    0.39
    Activations Density 0.000%

    No Known Activations