© 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. 70805
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
     OGSÅ
    -1.04
    Considering
    -0.93
    It
    -0.92
     same
    -0.92
     aturan
    -0.88
    Assuming
    -0.87
    You
    -0.85
     messa
    -0.85
    ีย
    -0.85
    \}=
    -0.82
    POSITIVE LOGITS
    TextBoxColumn
    1.00
     (
    0.92
     ref
    0.91
     ministros
    0.90
     when
    0.88
    
    0.88
     píše
    0.87
     historii
    0.87
     }{
    0.86
    Rendez
    0.85
    Activations Density 0.034%

    No Known Activations