© 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. 147536
    Prev
    Next
    INDEX
    Explanations

    reach heights or out full

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

    Everyday experience, production, translation

    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
    铁路
    0.47
    вшихся
    0.43
    kond
    0.43
    тивов
    0.43
    吵
    0.42
    ですよね
    0.42
    宽松
    0.42
    吆
    0.41
    可以使用
    0.40
    ાસ
    0.40
    POSITIVE LOGITS
     እ
    0.54
     travaille
    0.50
     ငါ
    0.50
     brother
    0.48
     audit
    0.47
     теркәлүсез
    0.47
     معنی
    0.47
     הח
    0.47
     â
    0.46
     قدم
    0.46
    Activations Density 0.001%

    No Known Activations