© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108148
    Prev
    Next
    INDEX
    Explanations

    currency price discount

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

    language and humor

    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
    Negative Logits
     ১৯
    0.45
    ема
    0.45
    ΕΣ
    0.44
    ми
    0.42
    는
    0.42
     Expression
    0.41
     coder
    0.41
    맨
    0.41
    源码
    0.41
    ῇ
    0.40
    POSITIVE LOGITS
    のお店
    0.46
    jsonplaceholder
    0.45
    が好き
    0.44
    詆
    0.43
    氾
    0.42
    好き
    0.41
    感慨
    0.41
     humorous
    0.40
    羡慕
    0.38
    discount
    0.38
    Activations Density 0.002%

    No Known Activations