© 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. 212296
    Prev
    Next
    INDEX
    Explanations

    emerging power or contracts

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

    both aspects

    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
    reszt
    0.51
    el
    0.49
     শাসক
    0.48
    tug
    0.48
    ETC
    0.48
    spiele
    0.48
    t
    0.47
    "][
    0.47
    al
    0.46
    encie
    0.46
    POSITIVE LOGITS
    ，
    0.49
    %，
    0.47
    難
    0.47
    Even
    0.45
    僅
    0.45
    ，「
    0.43
     έναν
    0.43
    根本
    0.42
    時
    0.42
    訂
    0.41
    Activations Density 0.000%

    No Known Activations