© 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. 10-GEMMASCOPE-RES-131K
    7. 22498
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     cj
    -1.10
    ꧁
    -1.09
    rester
    -1.07
     chong
    -1.06
     orto
    -1.06
     مختلفة
    -1.06
     horrend
    -1.05
     cali
    -1.04
     ALONE
    -1.04
    hört
    -1.03
    POSITIVE LOGITS
     it
    1.19
     we
    1.05
     Two
    1.02
     use
    1.02
     effective
    1.00
     breach
    0.99
     two
    0.98
     our
    0.96
     extensive
    0.96
    十大
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.