© 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. 98489
    Prev
    Next
    INDEX
    Explanations

    JavaScript code constructs

    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
    シーズン
    -0.84
    (
    -0.78
    一是
    -0.77
    つく
    -0.76
     verksamhet
    -0.75
    _
    -0.73
    nienia
    -0.72
    Feng
    -0.71
     fooled
    -0.71
    来讲
    -0.69
    POSITIVE LOGITS
     JSON
    1.60
    JSON
    1.41
    parseInt
    1.33
     Math
    1.02
     Number
    0.99
     Buffer
    0.95
     parseInt
    0.94
    merksamkeit
    0.91
    Number
    0.91
    parseFloat
    0.91
    Activations Density 0.008%

    No Known Activations