© 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-16K
    4. 654
    Prev
    Next
    INDEX
    Explanations

    CSS properties and Python code

    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_16k_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
    glycos
    0.35
    ("^
    0.30
    ResBuffer
    0.30
    NSDictionary
    0.27
    :@"
    0.27
    жаем
    0.26
    glRasterPos
    0.26
     thermocou
    0.26
    BOUND
    0.26
     कॉल्ड
    0.25
    POSITIVE LOGITS
     ۔
    0.32
    कोई
    0.29
    ุ
    0.29
     कोई
    0.28
     विरोधी
    0.28
     ۲۰
    0.28
     none
    0.28
     بہت
    0.27
    .</
    0.27
     பார்வை
    0.27
    Activations Density 0.516%

    No Known Activations