© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70623
    Prev
    Next
    INDEX
    Explanations

    software operations and components

    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
     nimmer
    -1.44
     alluring
    -1.26
     GENERAL
    -1.26
     mediocre
    -1.25
     erhi
    -1.23
     unbelievably
    -1.23
     semelh
    -1.21
     zubehör
    -1.21
     delikat
    -1.21
     heilige
    -1.20
    POSITIVE LOGITS
     on
    2.03
     in
    1.83
     so
    1.80
     to
    1.75
     at
    1.63
     with
    1.62
     now
    1.61
     as
    1.58
     using
    1.55
     without
    1.47
    Activations Density 0.065%

    No Known Activations