© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63027
    Prev
    Next
    INDEX
    Explanations

    Lefschetz, Inside, I, 2

    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
    ազ
    -0.82
     Glä
    -0.82
     Königin
    -0.81
    ların
    -0.78
    جوا
    -0.77
    териал
    -0.77
    kungen
    -0.77
    投
    -0.77
     Chemical
    -0.76
    ppins
    -0.76
    POSITIVE LOGITS
    setupUi
    1.33
     Ui
    1.02
    setObjectName
    0.83
     Marti
    0.80
    Ui
    0.76
     PREFIX
    0.74
    StoreMessageInfo
    0.73
    MCP
    0.73
     Milford
    0.73
     formy
    0.71
    Activations Density 0.005%

    No Known Activations