© 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. 53581
    Prev
    Next
    INDEX
    Explanations

    tools and quality

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

    questions about dates and methods

    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
    ディスク
    0.51
     FontSize
    0.46
    ZA
    0.45
    栯
    0.45
    λια
    0.44
    Utf
    0.44
    繊維
    0.43
     районов
    0.43
    掻
    0.43
    )!
    0.42
    POSITIVE LOGITS
    ंसारी
    0.48
     แจ
    0.47
    ქვენ
    0.47
    k
    0.46
    bust
    0.45
    gates
    0.44
     realiz
    0.44
    kran
    0.44
     ပြ
    0.44
     uner
    0.43
    Activations Density 0.001%

    No Known Activations