© 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. 60861
    Prev
    Next
    INDEX
    Explanations

    transitions between clauses

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

    explaining changes after each

    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
    獸
    0.54
    歟
    0.54
    ЛИ
    0.53
     당신
    0.51
    ⥤
    0.51
    넘
    0.50
    짊
    0.50
    謬
    0.50
    薀
    0.50
    ცია
    0.49
    POSITIVE LOGITS
     drei
    0.49
    company
    0.47
    external
    0.46
    am
    0.43
     flavorful
    0.43
     Lehrer
    0.43
     standalone
    0.43
     Thun
    0.42
     saben
    0.42
     Use
    0.42
    Activations Density 0.000%

    No Known Activations