© 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. 16614
    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
     oport
    -0.94
    REMOVE
    -0.86
     when
    -0.85
    бл
    -0.81
     hinter
    -0.81
    TUN
    -0.79
    mo
    -0.78
    的眼神
    -0.77
    严格
    -0.77
    boxylic
    -0.76
    POSITIVE LOGITS
     אנחנו
    0.94
     dwóch
    0.88
     бъде
    0.88
     två
    0.88
    equilibrium
    0.87
     obuv
    0.87
     trzech
    0.85
     különböző
    0.85
    无疑
    0.84
    diferentes
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.