© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 70090
    Prev
    Next
    INDEX
    Explanations

    data types and choices

    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
     DateTime
    -0.80
     math
    -0.79
     theorems
    -0.78
    ostom
    -0.76
    artifactId
    -0.75
    sumowanie
    -0.75
     tweeter
    -0.74
    uert
    -0.73
     asterisk
    -0.73
    šana
    -0.73
    POSITIVE LOGITS
     choices
    1.95
    choices
    1.69
    Choices
    1.60
     enum
    1.53
     choice
    1.53
     Choices
    1.50
    Enum
    1.46
     enums
    1.45
    ENUM
    1.44
     Enum
    1.42
    Activations Density 0.020%

    No Known Activations