© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25730
    Prev
    Next
    INDEX
    Explanations

    geopolitical entities and concepts

    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
    __':
    
    -1.01
     (!__
    -0.96
    __":
    
    -0.95
    buie
    -0.85
    ַּ
    -0.85
    kswagen
    -0.80
     voordelen
    -0.80
    argout
    -0.79
    setTimeout
    -0.79
    idł
    -0.78
    POSITIVE LOGITS
     from
    2.16
     desde
    1.85
     since
    1.77
     depuis
    1.64
     منذ
    1.49
     circa
    1.48
     before
    1.42
     till
    1.40
     between
    1.32
     từ
    1.30
    Activations Density 0.069%

    No Known Activations