© 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. 22-GEMMASCOPE-RES-131K
    7. 36618
    Prev
    Next
    INDEX
    Explanations

    code blocks with get/set or begin/end

    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_22/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
     gången
    -1.43
     rū
    -1.40
    ༵
    -1.40
    Поэтому
    -1.40
     which
    -1.39
    InkWell
    -1.38
    
    -1.38
    Opinión
    -1.36
     rağmen
    -1.35
    onyme
    -1.34
    POSITIVE LOGITS
     
    1.69
    if
    1.49
                
    1.45
    it
    1.44
    感じで
    1.41
    ものが
    1.38
     ähnlichen
    1.36
    嵓
    1.35
     brimming
    1.35
    ふと
    1.33
    Activations Density 0.004%

    No Known Activations