© 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. 80820
    Prev
    Next
    INDEX
    Explanations

    Werkzeug and Flask code

    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
     Sharpe
    -0.82
    iorgio
    -0.81
     Cari
    -0.77
    vidence
    -0.76
     tóc
    -0.75
     lips
    -0.75
    rums
    -0.75
    núť
    -0.75
     agri
    -0.75
     tre
    -0.74
    POSITIVE LOGITS
     flask
    1.16
     Flask
    1.16
    Flask
    1.10
    flask
    1.00
     Werkzeug
    0.93
     blueprints
    0.90
    blueprint
    0.86
    懺
    0.82
    jin
    0.81
     Alembic
    0.81
    Activations Density 0.033%

    No Known Activations