© 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. 882
    Prev
    Next
    INDEX
    Explanations

    amount of something

    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
    wiesen
    -1.31
     ouverts
    -1.28
    糌
    -1.26
    躂
    -1.25
     meeste
    -1.25
    赁
    -1.23
     vraiment
    -1.22
     veramente
    -1.22
    所有
    -1.21
     felicitación
    -1.20
    POSITIVE LOGITS
     from
    1.85
     over
    1.65
     information
    1.49
     that
    1.47
     help
    1.46
     extensa
    1.46
     both
    1.38
     allow
    1.38
     influence
    1.34
     complicada
    1.33
    Activations Density 0.243%

    No Known Activations