© 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. 28171
    Prev
    Next
    INDEX
    Explanations

    expressions of amusement or agreement

    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
     for
    -1.69
     with
    -1.67
     our
    -1.59
     an
    -1.55
     out
    -1.49
    ノリ
    -1.49
     using
    -1.45
     bolster
    -1.45
     by
    -1.43
     four
    -1.41
    POSITIVE LOGITS
    ⸢
    1.74
    ſſen
    1.69
    ⏑
    1.67
    沵
    1.63
    𓁹
    1.63
     byen
    1.60
     WHEN
    1.57
    鵙
    1.56
     navire
    1.54
    
    1.54
    Activations Density 0.193%

    No Known Activations