© 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. 65445
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     they
    -1.97
     you
    -1.94
    </strong>
    -1.80
     Give
    -1.76
           
    -1.76
            
    -1.66
     September
    -1.66
    Those
    -1.66
    when
    -1.60
     increases
    -1.59
    POSITIVE LOGITS
    퐸
    1.71
    𓁹
    1.70
    泺
    1.53
    喾
    1.52
    peut
    1.52
     musul
    1.47
     gada
    1.44
    '
    1.43
     diverses
    1.40
     eſt
    1.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.