© 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. 168270
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    bridges and viaducts

    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
    atien
    0.48
    제곱
    0.48
    ጥነት
    0.44
     smoothed
    0.43
     unab
    0.43
    賢
    0.43
    悚
    0.43
    '
    0.43
    ()'
    0.43
    [
    0.42
    POSITIVE LOGITS
    คุณ
    0.55
    на
    0.50
     você
    0.48
    अगर
    0.47
     démar
    0.46
     регистра
    0.46
    superclass
    0.46
     настройки
    0.46
     artículo
    0.45
    çok
    0.45
    Activations Density 0.001%

    No Known Activations