© 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. 32320
    Prev
    Next
    INDEX
    Explanations

    data types in 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
     invasive
    -0.78
    readObject
    -0.72
    emptive
    -0.71
     Valentine
    -0.71
    WebServlet
    -0.70
    ppar
    -0.70
    jazz
    -0.70
     étui
    -0.69
     الخام
    -0.69
    Aran
    -0.69
    POSITIVE LOGITS
     integer
    2.77
     Integer
    2.41
     string
    2.23
     boolean
    2.17
     String
    2.13
    integer
    2.11
    Integer
    2.08
     int
    2.00
     float
    1.96
     integers
    1.95
    Activations Density 0.284%

    No Known Activations