© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43976
    Prev
    Next
    INDEX
    Explanations

    primary and flow rates

    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
    pengaruhi
    0.48
    如果
    0.42
    widgetTo
    0.41
    书籍
    0.39
    perme
    0.39
    增强
    0.38
    的
    0.38
    ushima
    0.37
    IEnumerable
    0.37
    浓度
    0.37
    POSITIVE LOGITS
     EVs
    0.48
     zing
    0.47
     😊
    0.47
     Suburban
    0.46
     socialism
    0.46
    !“
    0.45
     Browns
    0.45
     ourselves
    0.44
     Sein
    0.44
     (#
    0.44
    Activations Density 0.004%

    No Known Activations