© 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. 16-GEMMASCOPE-2-RES-16K
    7. 767
    Prev
    Next
    INDEX
    Explanations

    years followed by punctuation

    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_16_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
    ד
    0.62
    сть
    0.54
    レー
    0.52
    د
    0.50
    ामध्ये
    0.49
    тину
    0.49
    ム
    0.48
    츠
    0.48
    ני
    0.48
    λα
    0.48
    POSITIVE LOGITS
     OF
    0.61
     Indien
    0.61
     of
    0.60
     THE
    0.59
     et
    0.59
     AB
    0.58
     ANTI
    0.58
     annen
    0.57
     ID
    0.56
     I
    0.56
    Activations Density 0.881%

    No Known Activations