© 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. 12316
    Prev
    Next
    INDEX
    Explanations

    automotive power

    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
     it
    -2.20
     eram
    -1.55
    饹
    -1.43
     essas
    -1.43
     calientes
    -1.40
     /
    -1.38
    Ᏺ
    -1.34
    瓮
    -1.33
     by
    -1.30
    連れて
    -1.30
    POSITIVE LOGITS
    开始
    1.63
     Архивировано
    1.61
    Of
    1.54
     început
    1.52
     dimentic
    1.52
     setiap
    1.50
    ᯾
    1.50
     organisiert
    1.49
    </h2>
    1.48
    
    1.48
    Activations Density 0.025%

    No Known Activations