© 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. 66402
    Prev
    Next
    INDEX
    Explanations

    prefix followed by punctuation or assignment

    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
    {
    -4.06
    or
    -3.50
    ↵↵
    -3.20
    [
    -2.97
    "
    -2.77
     .
    -2.72
    -
    -2.63
                        
    -2.59
    (
    -2.44
      
    -2.42
    POSITIVE LOGITS
    ጁ
    3.09
     車場
    3.08
     abiye
    2.95
     sayfa
    2.86
    鮠
    2.83
     saada
    2.75
    ‪.‬‬
    2.67
    哢
    2.66
    逖
    2.64
     diki
    2.61
    Activations Density 0.002%

    No Known Activations