© 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. 208026
    Prev
    Next
    INDEX
    Explanations

    phrases like "appropriate to" or "genres to"

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

    focused on clarity

    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
    ENDOR
    0.50
    𒋻
    0.49
     অনুগ্রহ
    0.48
     আবিষ্কার
    0.47
     ಆರೋಗ್ಯ
    0.47
     verstehen
    0.46
     اختبار
    0.46
    🥯
    0.46
     afectar
    0.46
     ahuv
    0.46
    POSITIVE LOGITS
     main
    0.53
    꼴
    0.50
     has
    0.46
     naz
    0.45
     bou
    0.45
    最
    0.44
     sl
    0.43
    сля
    0.43
    台
    0.42
    惮
    0.42
    Activations Density 0.000%

    No Known Activations