© 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. 153593
    Prev
    Next
    INDEX
    Explanations

    apple pies, island, NPS award

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

    writing assembly and similar technical content

    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
    诋
    0.52
    否定
    0.41
    辨
    0.40
    aliment
    0.39
    充
    0.39
    Assured
    0.38
    发言
    0.38
    记
    0.38
    逍
    0.38
    嘗試
    0.38
    POSITIVE LOGITS
     ต้องการ
    0.51
     demonstrated
    0.50
     membutuhkan
    0.49
    ต้องการ
    0.47
     үч
    0.46
    prj
    0.46
     তিন
    0.46
     لیون
    0.46
     subcontractor
    0.45
     passionately
    0.45
    Activations Density 0.004%

    No Known Activations