© 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. 106459
    Prev
    Next
    INDEX
    Explanations

    here to help

    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
    Support
    -1.00
     reassuring
    -0.82
    âmetro
    -0.81
    support
    -0.81
    Supports
    -0.81
    Accessors
    -0.80
    upport
    -0.80
    IIA
    -0.80
    月下
    -0.79
     OUTLINE
    -0.79
    POSITIVE LOGITS
     help
    3.66
     helps
    2.11
    help
    1.95
     Help
    1.94
     HELP
    1.91
    Help
    1.88
     helping
    1.88
     helfen
    1.80
    帮助
    1.77
     helped
    1.73
    Activations Density 0.059%

    No Known Activations