© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 7072
    Prev
    Next
    INDEX
    Explanations

    negative sentiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     disting
    1.07
    記念
    0.94
    anyi
    0.94
     synergies
    0.89
     ribosomal
    0.87
     liger
    0.86
     nifty
    0.86
     {'
    0.84
     QTL
    0.84
     motivic
    0.83
    POSITIVE LOGITS
     Terrible
    2.50
    Worst
    2.46
     cursed
    2.41
     Worse
    2.36
     Worst
    2.35
     ужа
    2.31
     scum
    2.30
    worst
    2.26
     ashamed
    2.21
     intolerable
    2.21
    Activations Density 0.179%

    No Known Activations