© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83878
    Prev
    Next
    INDEX
    Explanations

    afternoon times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    {
    -2.42
     '
    -1.99
     Notwithstanding
    -1.98
     feita
    -1.93
     porém
    -1.92
     —
    -1.89
    s
    -1.88
     
    -1.83
     However
    -1.76
    ↵
    -1.70
    POSITIVE LOGITS
     abiye
    2.48
    OUTUBE
    2.13
     kollu
    2.11
    踯
    2.08
    鈊
    2.05
     kapak
    2.00
     arkiv
    2.00
     sosi
    2.00
    when
    1.98
     aktar
    1.94
    Activations Density 0.004%

    No Known Activations