© 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. 42236
    Prev
    Next
    INDEX
    Explanations

    Elias, Adel, Providence

    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
    鴬
    -2.89
     hvem
    -2.75
    ⎚
    -2.64
    妗
    -2.63
    蕷
    -2.50
    𖥻
    -2.50
     получает
    -2.39
     definizione
    -2.34
    য়
    -2.34
     aina
    -2.33
    POSITIVE LOGITS
     \
    2.89
    .
    2.56
            
    2.33
    趼
    2.14
    </i>
    2.14
    ]
    2.06
     montagnes
    2.05
     have
    2.03
    зи
    1.99
    '],
    1.99
    Activations Density 0.008%

    No Known Activations