© 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. 16525
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     (
    -1.23
    classed
    -1.18
    leine
    -1.16
     iman
    -1.11
    juries
    -1.09
     þ
    -1.09
     unu
    -1.02
     sommer
    -0.99
     nao
    -0.98
     bula
    -0.98
    POSITIVE LOGITS
     explicó
    1.45
     detalló
    1.38
     elegir
    1.34
     tendrán
    1.33
     deberán
    1.32
     afirmó
    1.31
     cuál
    1.30
    )}_
    1.30
     supuestamente
    1.27
     señaló
    1.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.