© 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. 22-GEMMASCOPE-RES-131K
    7. 9769
    Prev
    Next
    INDEX
    Explanations

    entity names following delimiters

    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_22/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
    焢
    -1.57
    wendung
    -1.52
    我们
    -1.49
     procédures
    -1.48
     stratégies
    -1.46
     médicaments
    -1.45
     TÉ
    -1.44
    obten
    -1.44
     intensif
    -1.41
     första
    -1.40
    POSITIVE LOGITS
     other
    1.56
     more
    1.31
     everything
    1.28
     ,
    1.23
     all
    1.21
     such
    1.20
     both
    1.18
     same
    1.17
     anything
    1.16
     tudo
    1.15
    Activations Density 0.012%

    No Known Activations