© 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. 34-GEMMASCOPE-RES-131K
    4. 83793
    Prev
    Next
    INDEX
    Explanations

    scores and opponents

    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
    Not in Any Lists

    No Comments

    Negative Logits
     no
    -0.93
    purl
    -0.82
     pages
    -0.82
     پیشن
    -0.81
     echo
    -0.79
     stick
    -0.78
     магнит
    -0.77
    atology
    -0.73
    chriften
    -0.71
     média
    -0.71
    POSITIVE LOGITS
     decote
    0.94
     outs
    0.93
     rallied
    0.82
    scored
    0.81
    izability
    0.77
     erupted
    0.76
    trusted
    0.75
     fameux
    0.75
     quarterly
    0.75
     outperform
    0.75
    Activations Density 0.005%

    No Known Activations