© 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. 10-GEMMASCOPE-RES-131K
    7. 1210
    Prev
    Next
    INDEX
    Explanations

    class with numbered lists

    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
    ?».
    -1.97
     gewel
    -1.95
     riu
    -1.94
    阇
    -1.90
    醅
    -1.88
     kazak
    -1.88
    栳
    -1.88
    
    -1.87
    ?»
    -1.84
     sanat
    -1.84
    POSITIVE LOGITS
     of
    2.17
     You
    1.86
    l
    1.85
    <em>
    1.77
     destacan
    1.75
     být
    1.66
    <strong>
    1.63
    ;
    1.57
    or
    1.56
     einfachen
    1.55
    Activations Density 0.001%

    No Known Activations