© 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. 176721
    Prev
    Next
    INDEX
    Explanations

    various languages or scripts

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

    newly options

    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
     Explain
    0.46
     kosm
    0.45
     কেবলমাত্র
    0.44
     bereaved
    0.43
     পুরাণ
    0.43
     tracing
    0.42
     cosmology
    0.41
     ತಮ್ಮ
    0.41
    }}-\
    0.41
     deprive
    0.41
    POSITIVE LOGITS
    بن
    0.55
    nes
    0.50
    น์
    0.50
    бен
    0.45
    nesto
    0.44
    वें
    0.43
    נע
    0.42
     rápidamente
    0.41
    چال
    0.41
    ρεί
    0.41
    Activations Density 0.001%

    No Known Activations