© 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. 58031
    Prev
    Next
    INDEX
    Explanations

    right followed by parenthesis

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     However
    -3.28
    Despite
    -3.14
     enhance
    -3.13
     Despite
    -2.97
     When
    -2.97
    when
    -2.92
    When
    -2.80
    t
    -2.80
    Even
    -2.80
     facilitate
    -2.77
    POSITIVE LOGITS
     será
    3.34
     soooo
    3.25
    
    3.22
     extremely
    3.17
     sooo
    3.17
     hugely
    3.13
     famed
    3.13
     superb
    3.11
     acclaimed
    3.11
     momentous
    3.09
    Activations Density 0.001%

    No Known Activations