© 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. 157684
    Prev
    Next
    INDEX
    Explanations

    activities, prospects, results, forms

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

    code formatting and special characters

    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
    x
    0.53
     trom
    0.49
    ni
    0.48
    ium
    0.47
    na
    0.47
    d
    0.46
    using
    0.45
    해
    0.45
    test
    0.45
    ng
    0.45
    POSITIVE LOGITS
     расположение
    0.50
    MathOperator
    0.49
     захворю
    0.48
     oberen
    0.47
     surnames
    0.47
     ви
    0.46
     ንጥረ
    0.46
     شمال
    0.46
     صہی
    0.46
     Saccharomyces
    0.46
    Activations Density 0.002%

    No Known Activations