© 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. 47970
    Prev
    Next
    INDEX
    Explanations

    numeric calculation

    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
     There
    -2.77
     by
    -2.66
     as
    -2.64
     
    -2.61
     to
    -2.55
     What
    -2.55
     From
    -2.45
     not
    -2.42
     Just
    -2.42
     On
    -2.39
    POSITIVE LOGITS
     elektrik
    2.95
    饜
    2.91
     capucha
    2.78
    雠
    2.70
     kollu
    2.69
    傒
    2.64
     torba
    2.63
     diki
    2.59
     dekoratif
    2.59
     maksi
    2.56
    Activations Density 0.069%

    No Known Activations