© 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. 210508
    Prev
    Next
    INDEX
    Explanations

    sequence from specific words

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

    rapidly during

    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
    일
    0.68
    법
    0.57
    ى
    0.56
    I
    0.55
    마
    0.54
    당
    0.53
    레
    0.53
    하
    0.52
    Mon
    0.52
    공
    0.52
    POSITIVE LOGITS
     ଚ
    0.49
     Cadet
    0.49
     अत्यधिक
    0.49
     cadet
    0.49
     kome
    0.48
     вслед
    0.47
     самому
    0.47
     পিছনে
    0.45
     !}{
    0.45
     FID
    0.44
    Activations Density 0.000%

    No Known Activations