© 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. 205358
    Prev
    Next
    INDEX
    Explanations

    sales direct, growth of, Instagram @, work well

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

    words followed by 'directamente'

    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
     ich
    0.55
    カリ
    0.54
    മുഖ
    0.51
    汚
    0.51
    畬
    0.48
    タニ
    0.47
    piperidin
    0.46
    ಯೇ
    0.46
    ង់
    0.45
    ك
    0.45
    POSITIVE LOGITS
    不喜欢
    0.52
    กัน
    0.49
    keyword
    0.48
    关键字
    0.47
    allelujah
    0.47
    ™.
    0.44
    聪
    0.44
     ক্ষেপ
    0.43
    ệu
    0.43
    婪
    0.43
    Activations Density 0.000%

    No Known Activations