© 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. 22-GEMMASCOPE-RES-131K
    7. 16694
    Prev
    Next
    INDEX
    Explanations

    funny jokes

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    était
    -0.97
     people
    -0.93
     hh
    -0.87
     ppl
    -0.86
    silien
    -0.84
     хуже
    -0.84
    フィック
    -0.82
     you
    -0.82
     Lice
    -0.82
     EVERYTHING
    -0.81
    POSITIVE LOGITS
     into
    1.16
    ització
    1.13
     భూ
    1.07
     cukru
    1.05
     doba
    1.02
     mojej
    0.99
     farby
    0.98
    performed
    0.98
     falou
    0.98
     mukaan
    0.97
    Activations Density 0.230%

    No Known Activations