© 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. 16752
    Prev
    Next
    INDEX
    Explanations

    cause and effect

    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
     UIT
    -1.01
    voyer
    -0.97
    Clasificación
    -0.94
    *****/
    -0.93
    Transk
    -0.92
    newblock
    -0.91
     _$
    -0.91
    urned
    -0.91
    zków
    -0.91
     Annales
    -0.90
    POSITIVE LOGITS
     corresponding
    1.00
     for
    0.99
     niž
    0.93
     oznacza
    0.93
     perhatian
    0.89
     correspondingly
    0.89
     счастья
    0.88
     reduced
    0.87
     Einleitung
    0.86
     silnik
    0.85
    Activations Density 0.098%

    No Known Activations