© 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. 16635
    Prev
    Next
    INDEX
    Explanations

    numbers and abbreviations

    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
     联
    -0.93
     distor
    -0.91
     twister
    -0.89
    ânia
    -0.87
     profite
    -0.86
     sobri
    -0.85
     aton
    -0.84
    Elke
    -0.84
     psychiat
    -0.84
     vehe
    -0.82
    POSITIVE LOGITS
     delikat
    0.93
     csapat
    0.93
     Garantía
    0.92
    sores
    0.89
     general
    0.88
    HttpEntity
    0.88
     structure
    0.87
     acostumb
    0.85
    zwald
    0.85
     our
    0.85
    Activations Density 0.041%

    No Known Activations