© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43714
    Prev
    Next
    INDEX
    Explanations

    decoder and serializer context

    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
    a
    -5.03
    :
    -3.63
    s
    -3.52
    ”
    -3.50
    ↵↵
    -3.33
    $
    -3.30
    \
    -3.23
    1
    -3.16
    [
    -3.09
     {
    -3.00
    POSITIVE LOGITS
    zelfde
    3.28
    ⃤
    3.03
    
    2.86
     semelhante
    2.77
    鳙
    2.75
    dientemente
    2.75
     farba
    2.75
    绺
    2.72
    
    2.69
    趼
    2.69
    Activations Density 0.002%

    No Known Activations