© 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. 172033
    Prev
    Next
    INDEX
    Explanations

    achieved online from the reservation

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

    headings and summaries

    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
     Ц
    0.49
     baju
    0.49
    ны
    0.48
     advancing
    0.47
     Notation
    0.46
    as
    0.46
     connecting
    0.46
     ৫০
    0.46
     abrasion
    0.46
    уга
    0.46
    POSITIVE LOGITS
     titoli
    0.46
    Christine
    0.46
     esempl
    0.45
     گویا
    0.45
    ]-[
    0.45
    Cory
    0.45
     كلها
    0.44
    yon
    0.44
    ရား
    0.43
    tte
    0.43
    Activations Density 0.001%

    No Known Activations