© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11641
    Prev
    Next
    INDEX
    Explanations

    language codes in urls

    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_31_width_16k_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
    悚
    0.46
    ঘট
    0.46
    ূত
    0.46
     प्रेर
    0.44
    相同的
    0.44
     ktor
    0.43
     पौधों
    0.43
     mimo
    0.42
     দ্রব
    0.42
    QUrl
    0.42
    POSITIVE LOGITS
    en
    0.63
    er
    0.50
    -
    0.46
    ن
    0.46
    ed
    0.45
    no
    0.45
    los
    0.44
    sole
    0.44
    in
    0.44
    ang
    0.43
    Activations Density 0.045%

    No Known Activations