© 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. 70456
    Prev
    Next
    INDEX
    Explanations

    phase

    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
    -2.36
    8
    -1.94
    ;
    
    -1.76
    1
    -1.76
    7
    -1.70
    3
    -1.69
    which
    -1.66
    :");
    
    -1.65
     uzyskać
    -1.59
    you
    -1.54
    POSITIVE LOGITS
     Porque
    1.87
     ambas
    1.62
    rechter
    1.50
     leur
    1.45
     BOTH
    1.45
    ㌧
    1.45
    Porque
    1.44
    да
    1.41
    ſtion
    1.40
     ideale
    1.39
    Activations Density 0.035%

    No Known Activations