© 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. 112884
    Prev
    Next
    INDEX
    Explanations

    me unto, you download, taught, textile, centrifuge, us, fans neighbours

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

    concepts and relationships

    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
    ar
    0.56
    uity
    0.47
    ра
    0.47
    ilina
    0.47
    。
    0.46
    ，
    0.46
    Ary
    0.46
    и
    0.46
    orio
    0.44
    man
    0.44
    POSITIVE LOGITS
     sı
    0.49
    மாட்ட
    0.46
     başka
    0.46
     کبھی
    0.46
     yukarı
    0.46
    规定的
    0.46
    จะไม่
    0.46
     क्रमशः
    0.45
     सूर्य
    0.45
     विभाजन
    0.45
    Activations Density 0.001%

    No Known Activations