© 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. 211678
    Prev
    Next
    INDEX
    Explanations

    collocations and sequences

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

    multilingual temporal context

    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
    t
    0.47
    o
    0.47
    ft
    0.46
    fs
    0.45
    fields
    0.45
    LEMN
    0.45
    ចាយ
    0.44
    leValue
    0.43
    y
    0.43
     만큼
    0.43
    POSITIVE LOGITS
     thường
    0.52
    لق
    0.51
     När
    0.51
     jäl
    0.48
     spesso
    0.46
     menyebabkan
    0.46
     або
    0.45
     szer
    0.45
     Ahora
    0.45
     när
    0.45
    Activations Density 0.001%

    No Known Activations