© 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. 42395
    Prev
    Next
    INDEX
    Explanations

    improvement of something

    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
    是
    -3.33
    2
    -3.20
    蕷
    -3.03
    镦
    -2.94
    价格
    -2.80
    or
    -2.78
    しっかり
    -2.69
    e
    -2.69
    秾
    -2.64
     humeur
    -2.63
    POSITIVE LOGITS
    趼
    4.13
    汭
    3.77
    弍
    3.48
    姈
    3.30
    .
    3.25
    觏
    3.13
    酲
    3.13
    聼
    3.05
    
    2.97
     of
    2.92
    Activations Density 0.008%

    No Known Activations