© 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. 10-GEMMASCOPE-RES-131K
    7. 12152
    Prev
    Next
    INDEX
    Explanations

    demonstratives and intensifiers

    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_10/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
    鷽
    -1.94
    镲
    -1.84
    嗞
    -1.71
    鱨
    -1.70
     広場
    -1.70
     ugyan
    -1.70
    
    -1.68
    鋦
    -1.64
    こいつ
    -1.63
     手绘
    -1.59
    POSITIVE LOGITS
     will
    2.20
     have
    2.19
     can
    1.94
     we
    1.82
     first
    1.79
     two
    1.77
     use
    1.74
     one
    1.73
     now
    1.73
     from
    1.71
    Activations Density 0.011%

    No Known Activations