© 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. 34-GEMMASCOPE-RES-131K
    7. 3620
    Prev
    Next
    INDEX
    Explanations

    ExclusionPolicy("all")

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Monument
    -0.85
     moletom
    -0.79
     errorMessage
    -0.77
     confin
    -0.75
    errorMessage
    -0.75
     eletrônico
    -0.74
     multiplied
    -0.73
     inmig
    -0.73
    アレルギー
    -0.73
     madrid
    -0.71
    POSITIVE LOGITS
     inclusion
    0.84
     Include
    0.79
     Ж
    0.79
     include
    0.77
    ovo
    0.76
    fasterxml
    0.76
     niem
    0.75
     näky
    0.75
    neapolis
    0.74
    ELIN
    0.74
    Activations Density 0.011%

    No Known Activations