© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128444
    Prev
    Next
    INDEX
    Explanations

    cycle related words 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_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
    を中心
    -2.80
    をはじめ
    -2.75
    鷥
    -2.70
     ペア
    -2.69
    瀦
    -2.67
     continually
    -2.67
    を始め
    -2.59
    眛
    -2.53
    
    -2.52
    猡
    -2.48
    POSITIVE LOGITS
    If
    3.14
     dodgy
    2.86
    They
    2.78
    ៚
    2.67
     selben
    2.56
    で
    2.52
     adaptar
    2.50
     ajustar
    2.47
    👉
    2.45
     dotyczące
    2.41
    Activations Density 0.012%

    No Known Activations