© 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. 47224
    Prev
    Next
    INDEX
    Explanations

    main function/method

    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
    勛
    -0.90
     informaci
    -0.89
     Croatian
    -0.84
     instruk
    -0.84
     gwaran
    -0.83
     Walmart
    -0.82
     Industry
    -0.81
    ഋ
    -0.81
     navideña
    -0.81
     adjunto
    -0.80
    POSITIVE LOGITS
     emplois
    0.79
    Launcher
    0.78
    istema
    0.75
     היי
    0.73
     Democ
    0.71
    wiz
    0.70
    launcher
    0.69
     whilst
    0.69
     HART
    0.69
    Rela
    0.68
    Activations Density 0.002%

    No Known Activations