© 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. 219558
    Prev
    Next
    INDEX
    Explanations

    after review or questions

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

    crucial screening or impulse correction

    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
    רוי
    0.50
     slip
    0.47
     Pier
    0.46
    وراق
    0.45
    トル
    0.44
    Pier
    0.44
     Instructional
    0.43
    껌
    0.43
     Wilmington
    0.42
    韦
    0.42
    POSITIVE LOGITS
    kých
    0.50
    te
    0.47
    meden
    0.46
     t
    0.44
    lu
    0.44
    wijl
    0.44
    dur
    0.43
     mä
    0.43
     aumento
    0.43
    ONDER
    0.43
    Activations Density 0.000%

    No Known Activations