© 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. 42275
    Prev
    Next
    INDEX
    Explanations

    similar variants or errors

    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
    蛱
    -2.66
    猡
    -2.30
    
    -2.28
    
    -2.27
    Ꭳ
    -2.19
    ſſen
    -2.17
    屃
    -2.16
     imprimible
    -2.11
    uties
    -2.11
     壁纸
    -2.11
    POSITIVE LOGITS
    </h3>
    2.44
    </i>
    2.11
    1
    2.00
     ,
    1.93
     ‘
    1.86
     beliebt
    1.86
    感じで
    1.81
    </strong>
    1.81
    他的
    1.80
     –
    1.80
    Activations Density 0.003%

    No Known Activations