© 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-16K
    7. 11378
    Prev
    Next
    INDEX
    Explanations

    satisfied with purchase

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

    expressed satisfaction or dissatisfaction

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     резер
    0.45
    絭
    0.44
    میٹ
    0.41
    ٹس
    0.40
    䚰
    0.39
    gek
    0.38
    ларни
    0.38
    ѡ
    0.38
     jederzeit
    0.37
     وكل
    0.37
    POSITIVE LOGITS
     performance
    0.49
     dissatisfied
    0.49
     dissatisfaction
    0.48
     unsatisfied
    0.45
     Sharjah
    0.45
     decide
    0.45
     refute
    0.42
     unbearable
    0.41
     paro
    0.41
     pola
    0.41
    Activations Density 0.014%

    No Known Activations