© 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. 9385
    Prev
    Next
    INDEX
    Explanations

    majority vote

    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
     nossas
    -1.90
     europeo
    -1.73
     …
    -1.72
    TintMode
    -1.68
     reconoc
    -1.66
    </u>
    -1.66
     nossos
    -1.65
     hallmark
    -1.63
    ised
    -1.63
    ман
    -1.62
    POSITIVE LOGITS
    Doge
    1.91
    鈊
    1.80
    妡
    1.78
     Songtext
    1.75
    Това
    1.73
    ﮯ
    1.72
     поможет
    1.69
    
    1.67
    》，
    1.66
    ޞ
    1.66
    Activations Density 0.009%

    No Known Activations