© 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. 24609
    Prev
    Next
    INDEX
    Explanations

    ANSI, algorithms, provisions, spee d s

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

    code and mathematics

    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
     mảnh
    0.46
    大佬
    0.44
    原来的
    0.43
    дора
    0.43
     গ্রেপ্তার
    0.40
     quill
    0.39
    稿
    0.39
    ..
    0.39
    凑
    0.39
     daddy
    0.38
    POSITIVE LOGITS
    ATION
    0.46
     provisions
    0.45
    netics
    0.45
    motions
    0.44
     lags
    0.43
    speeds
    0.43
    स्टिव
    0.42
    minutes
    0.41
    lovens
    0.41
    algorithms
    0.40
    Activations Density 0.000%

    No Known Activations