© 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. 10-GEMMASCOPE-RES-131K
    4. 59898
    Prev
    Next
    INDEX
    Explanations

    contrast and examples

    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_10/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
     that
    -1.68
     in
    -1.67
     to
    -1.66
     it
    -1.53
    蒾
    -1.41
     will
    -1.37
     with
    -1.32
     setelah
    -1.31
    \},
    -1.30
     Lainnya
    -1.30
    POSITIVE LOGITS
     herunter
    1.54
    
    1.30
    
    1.30
     possède
    1.27
    
    1.27
    .
    1.26
     varje
    1.23
     kapcs
    1.23
     herab
    1.23
     morgens
    1.23
    Activations Density 0.072%

    No Known Activations