© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17169
    Prev
    Next
    INDEX
    Explanations

    within

    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
    tails
    0.71
    el
    0.69
    elbe
    0.68
    bleeds
    0.67
    ტის
    0.64
    د
    0.64
     ομά
    0.64
    ा
    0.63
     fights
    0.63
    ı
    0.62
    POSITIVE LOGITS
    কে
    0.78
    ні
    0.75
    на
    0.74
    ین
    0.68
    не
    0.67
     notte
    0.67
     neuer
    0.64
     nacht
    0.64
     wohl
    0.64
    ات
    0.64
    Activations Density 0.019%

    No Known Activations