© 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. 85268
    Prev
    Next
    INDEX
    Explanations

    due to, holiday techniques

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

    Application, app, builder, segments, current

    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
    我已经
    0.54
    ចុ
    0.50
     проблем
    0.49
     громад
    0.49
    ى
    0.49
    jian
    0.48
     ২০১৩
    0.47
     على
    0.47
    joon
    0.46
     цих
    0.46
    POSITIVE LOGITS
     notifier
    0.46
    乂
    0.46
     administratif
    0.46
     hasht
    0.45
     dehyd
    0.45
    榀
    0.45
    朲
    0.45
    BAT
    0.44
     créer
    0.44
    懸
    0.44
    Activations Density 0.000%

    No Known Activations