© 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. 1007
    Prev
    Next
    INDEX
    Explanations

    what do you

    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
    媖
    -2.70
    訁
    -2.34
     biß
    -2.14
    вгений
    -2.03
     Inſ
    -1.95
    㩒
    -1.91
    푆
    -1.88
     ſou
    -1.88
    玉ねぎ
    -1.88
     dando
    -1.85
    POSITIVE LOGITS
     this
    2.27
    廊下
    1.98
     they
    1.78
    入り口
    1.73
    詫
    1.64
     formidable
    1.64
     which
    1.64
    忖
    1.55
    棠
    1.55
    并将
    1.52
    Activations Density 0.016%

    No Known Activations