© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 29911
    Prev
    Next
    INDEX
    Explanations

    Fitz or Fritz names

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     focusing
    -0.91
    ̞
    -0.82
    メタ
    -0.77
     datas
    -0.76
     समी
    -0.72
    Savings
    -0.70
    ならず
    -0.70
    sierra
    -0.70
    dois
    -0.69
     ASAP
    -0.69
    POSITIVE LOGITS
    roy
    1.09
     Fitz
    0.90
     bidra
    0.82
     Toussaint
    0.82
    Gerald
    0.81
     leakage
    0.80
    gib
    0.80
     språk
    0.79
     Gerald
    0.79
    nanoTime
    0.79
    Activations Density 0.013%

    No Known Activations