© 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. 19146
    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
    茕
    -1.76
    wouldn
    -1.66
    easily
    -1.62
    鲩
    -1.59
    honestly
    -1.58
     itt
    -1.56
    wasn
    -1.52
    unfortunately
    -1.51
    everybody
    -1.50
     แต่
    -1.49
    POSITIVE LOGITS
    The
    1.78
     first
    1.70
     when
    1.68
    On
    1.66
    We
    1.65
     actually
    1.64
    اعي
    1.63
     endast
    1.63
    This
    1.61
    Not
    1.61
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.