© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 84513
    Prev
    Next
    INDEX
    Explanations

    google account

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    有點
    0.49
    blanc
    0.48
     droite
    0.47
    有点
    0.45
    쿱
    0.45
    穿越
    0.44
    传承
    0.44
    ب
    0.44
     loy
    0.43
    ដៃ
    0.43
    POSITIVE LOGITS
     isomer
    0.45
    ว่า
    0.44
     প্রধান
    0.41
     کہ
    0.41
     Tako
    0.40
     pelajar
    0.40
     bahwa
    0.39
     prophecies
    0.39
    จำเป็น
    0.38
     Hik
    0.38
    Activations Density 0.002%

    No Known Activations