© 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. 61207
    Prev
    Next
    INDEX
    Explanations

    Woodbridge, Knoebel, Loughlin, Snohomish

    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
    剮
    -3.06
    ſelves
    -2.94
     變
    -2.73
    us
    -2.58
    Eglise
    -2.50
     onze
    -2.48
     當
    -2.42
     августа
    -2.42
    鲼
    -2.41
     裝
    -2.39
    POSITIVE LOGITS
    寕
    2.59
     ribuan
    2.55
    ción
    2.48
    鳧
    2.48
    </h3>
    2.45
    絎
    2.42
     núm
    2.42
    缓缓
    2.41
     ſever
    2.41
    赑
    2.38
    Activations Density 0.002%

    No Known Activations