© 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. 51316
    Prev
    Next
    INDEX
    Explanations

    good number, this book

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

    suggesting supervision or fantasy

    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
    ו
    0.46
    m
    0.43
    они
    0.43
    ตี
    0.43
    แก
    0.42
    毎週
    0.42
    োন
    0.42
    ведено
    0.41
    ६
    0.41
    ron
    0.40
    POSITIVE LOGITS
     organelles
    0.51
     apoptosis
    0.49
     mischief
    0.48
    arcz
    0.48
     colaboradores
    0.48
     জড়ের
    0.47
     unseres
    0.47
     Bodies
    0.46
     cytoskeleton
    0.46
     autoimmune
    0.46
    Activations Density 0.000%

    No Known Activations