© 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-16K
    7. 11311
    Prev
    Next
    INDEX
    Explanations

    price

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

    numbers, math, code, currency

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ین
    0.50
    Happy
    0.49
    주
    0.48
    in
    0.47
    High
    0.46
    June
    0.45
    レ
    0.45
    Through
    0.44
    フライ
    0.43
    Rasp
    0.43
    POSITIVE LOGITS
     perkembangan
    0.46
     ﺍ
    0.46
     Escherichia
    0.46
     Phyt
    0.46
     syarat
    0.46
     Pharmaceuticals
    0.45
     cellulaire
    0.45
     Kerja
    0.45
     dinding
    0.45
     ESL
    0.45
    Activations Density 0.011%

    No Known Activations