© 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. 71478
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
     or
    -1.88
     for
    -1.77
     because
    -1.69
     through
    -1.62
     as
    -1.35
     to
    -1.35
     so
    -1.34
     while
    -1.34
     then
    -1.31
     their
    -1.30
    POSITIVE LOGITS
     autonomie
    1.52
     obti
    1.41
     susc
    1.34
     registre
    1.28
    
    1.26
     plafon
    1.26
     meub
    1.25
     caneta
    1.25
     alarme
    1.24
     envelo
    1.24
    Activations Density 0.063%

    No Known Activations