© 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. 41438
    Prev
    Next
    INDEX
    Explanations

    code/configuration files

    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
    re
    -1.49
     -
    -1.49
    n
    -1.45
     fomentar
    -1.41
     who
    -1.40
    f
    -1.39
    t
    -1.39
    al
    -1.38
    していない
    -1.37
    猟
    -1.34
    POSITIVE LOGITS
     kitu
    1.64
     kasa
    1.62
     kafe
    1.59
     kriminal
    1.53
    تفسير
    1.52
     seksual
    1.48
     kosme
    1.48
     ekst
    1.47
     luks
    1.46
     serien
    1.42
    Activations Density 0.031%

    No Known Activations