© 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. 32954
    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
    Not in Any Lists

    No Comments

    Negative Logits
    isinin
    -0.91
    ╩
    -0.85
     there
    -0.85
     erik
    -0.82
    病気
    -0.82
    assertSame
    -0.81
    utsches
    -0.80
    ḇ
    -0.79
    ïc
    -0.79
    There
    -0.78
    POSITIVE LOGITS
    մ
    0.90
    的
    0.85
    andag
    0.85
    の
    0.84
     имел
    0.84
    ophysical
    0.82
     الشرطة
    0.82
    ろ
    0.82
     messaggi
    0.82
     months
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.