© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 29472
    Prev
    Next
    INDEX
    Explanations

    Creative Commons attribution non-commercial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    T
    0.62
    ري
    0.55
    Α
    0.54
    рты
    0.54
    ()):
    0.52
    ره
    0.52
    ете
    0.52
     фи
    0.50
    БУ
    0.50
     colo
    0.49
    POSITIVE LOGITS
     izd
    0.59
    も
    0.57
    hesda
    0.54
    ingen
    0.51
    othic
    0.50
    ermann
    0.50
    不堪
    0.50
    ing
    0.49
    eneo
    0.49
    hens
    0.49
    Activations Density 0.011%

    No Known Activations