© 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. 9533
    Prev
    Next
    INDEX
    Explanations

    left and below directionals

    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
     for
    -2.44
     in
    -1.99
     that
    -1.62
     or
    -1.56
     to
    -1.56
     as
    -1.53
     with
    -1.41
     may
    -1.40
     it
    -1.40
     will
    -1.37
    POSITIVE LOGITS
     alcune
    1.60
     alcuni
    1.34
     photos
    1.31
    licans
    1.27
     limpar
    1.24
    Zitat
    1.23
    
    1.23
     photographs
    1.23
     cojín
    1.23
     verschillende
    1.20
    Activations Density 0.015%

    No Known Activations