© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64494
    Prev
    Next
    INDEX
    Explanations

    superhero and character names

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Mv
    -0.76
    sequelize
    -0.76
    fige
    -0.74
     Animate
    -0.74
     nico
    -0.71
     Folly
    -0.71
     Lizzy
    -0.71
    Antony
    -0.71
     dashes
    -0.70
    姐
    -0.70
    POSITIVE LOGITS
     Flag
    0.78
    橿
    0.74
    idue
    0.74
     Issue
    0.73
    Ibn
    0.73
    inex
    0.72
     óra
    0.72
    QB
    0.70
     Singh
    0.69
    ultar
    0.68
    Activations Density 0.028%

    No Known Activations