© 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. 150683
    Prev
    Next
    INDEX
    Explanations

    converting checkout pages

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

    industrial circuit, collaborative governance

    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
     inheriting
    0.47
    шек
    0.44
    继承
    0.44
    वेदन
    0.43
    趋
    0.43
    सीमा
    0.42
    ₸
    0.42
    ویت
    0.42
    шку
    0.41
     subsequ
    0.41
    POSITIVE LOGITS
    賄
    0.51
     täglich
    0.47
     fand
    0.47
     b
    0.45
     ha
    0.44
    ’
    0.44
     ä
    0.44
     transmembrane
    0.43
     তথাপি
    0.43
    ।'
    0.43
    Activations Density 0.002%

    No Known Activations