© 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. 119114
    Prev
    Next
    INDEX
    Explanations

    type classification

    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
    setBounds
    -0.93
    innerHeight
    -0.91
     konci
    -0.90
     FirstName
    -0.90
    dataIndex
    -0.89
    relativeTime
    -0.86
    getOutputStream
    -0.86
    จำนวน
    -0.85
    mmation
    -0.84
    années
    -0.84
    POSITIVE LOGITS
     type
    1.59
     genre
    1.41
     classification
    1.34
     types
    1.29
     preferred
    1.26
    typeOf
    1.24
     jenis
    1.18
     प्रकार
    1.18
     chosen
    1.16
    Enumerated
    1.16
    Activations Density 0.059%

    No Known Activations