© 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. 102408
    Prev
    Next
    INDEX
    Explanations

    class and type references

    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
    MethodName
    -0.99
     name
    -0.83
     fieldName
    -0.78
     methodName
    -0.77
     names
    -0.77
     setName
    -0.75
    artal
    -0.75
    文件名
    -0.75
     marketing
    -0.73
     営業
    -0.73
    POSITIVE LOGITS
     type
    1.09
     clazz
    1.02
     cls
    0.95
     expected
    0.91
     types
    0.89
    itemType
    0.86
     cl
    0.86
     classes
    0.83
     requested
    0.83
     Expected
    0.82
    Activations Density 0.028%

    No Known Activations