© 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. 141507
    Prev
    Next
    INDEX
    Explanations

    wish lists, items, and need

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

    technical jargon, conferences, or topics

    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
    פ
    0.30
    ע
    0.29
    Ꮴ
    0.27
     മിക
    0.26
     పార్టీ
    0.26
     ቤ
    0.26
     incluem
    0.26
     pihaknya
    0.26
     incluidos
    0.26
     fő
    0.25
    POSITIVE LOGITS
     atthe
    0.23
     Western
    0.21
     ).
    0.21
    etan
    0.21
    려고
    0.21
     เงี้ย
    0.21
     Delaware
    0.20
    atanam
    0.20
     socalled
    0.20
    <eos>
    0.20
    Activations Density 0.287%

    No Known Activations