© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65736
    Prev
    Next
    INDEX
    Explanations

    GaN and silicon carbide

    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
     ferrovia
    -1.91
    
    -1.77
    辐射
    -1.68
    ⛦
    -1.55
     présidenti
    -1.52
    炻
    -1.51
    𓆝
    -1.47
     législ
    -1.46
     this
    -1.45
     investir
    -1.45
    POSITIVE LOGITS
    </h1>
    1.77
    </i>
    1.42
    ↵↵
    1.37
     \&
    1.34
    \}$,
    1.32
    Made
    1.30
    LETIN
    1.28
    )
    1.27
    matchCondition
    1.25
     [
    1.24
    Activations Density 0.037%

    No Known Activations