© 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. 23759
    Prev
    Next
    INDEX
    Explanations

    experimental programming features

    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
     willows
    -0.75
    setPreferredSize
    -0.70
    自带
    -0.69
    لقاء
    -0.68
    gerichts
    -0.68
     保証
    -0.67
    ciato
    -0.66
    навли
    -0.65
    success
    -0.65
    їв
    -0.65
    POSITIVE LOGITS
     experimental
    1.70
     feature
    1.64
    experimental
    1.63
    Experimental
    1.55
     Experimental
    1.55
     features
    1.52
     Feature
    1.44
    Feature
    1.39
    feature
    1.34
    FEATURE
    1.30
    Activations Density 0.127%

    No Known Activations