© 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. 141202
    Prev
    Next
    INDEX
    Explanations

    CCTV imagery and reduction

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

    Date, time, and intervals

    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
    아
    0.50
    ྛ
    0.48
    olução
    0.45
    DE
    0.45
    RA
    0.44
    （
    0.44
    ról
    0.44
    ø
    0.44
    ‌ها
    0.44
    恩
    0.43
    POSITIVE LOGITS
     आपूर्ति
    0.59
     pren
    0.53
     Verständ
    0.52
     капита
    0.51
     rescaling
    0.51
     erasing
    0.51
     нейтро
    0.51
     fold
    0.50
     င
    0.50
     кон
    0.49
    Activations Density 0.000%

    No Known Activations