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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119120
    Prev
    Next
    INDEX
    Explanations

    command line help and usage

    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
    рные
    -0.81
    ميل
    -0.81
    BD
    -0.76
    ISSN
    -0.75
     reports
    -0.73
    zestaw
    -0.71
     vlož
    -0.71
    udit
    -0.71
     positivity
    -0.70
    пів
    -0.69
    POSITIVE LOGITS
     help
    3.05
    help
    2.45
    Help
    2.16
     Help
    2.05
     HELP
    1.91
    帮助
    1.78
     usage
    1.74
     helping
    1.57
     Hilfe
    1.55
    HELP
    1.50
    Activations Density 0.044%

    No Known Activations