© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101507
    Prev
    Next
    INDEX
    Explanations

    Unicode, UTF-8, UTF-16, runes

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

    references to Unicode, UTF-16, and character encoding systems.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     atau
    -1.68
     или
    -1.67
     alebo
    -1.64
    y
    -1.63
     veya
    -1.61
    xide
    -1.58
     ragazza
    -1.58
    ",
    -1.57
    by
    -1.55
    '}
    -1.55
    POSITIVE LOGITS
     Почему
    1.70
     verschieden
    1.65
     Профиль
    1.59
     intrepid
    1.58
     Lately
    1.58
     Debido
    1.57
     brou
    1.56
     conhecida
    1.53
     Porque
    1.52
     Dentro
    1.51
    Activations Density 0.005%

    No Known Activations