© 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. 92326
    Prev
    Next
    INDEX
    Explanations

    java package declarations

    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
     without
    -1.13
     then
    -1.12
     because
    -1.01
     and
    -0.97
    monary
    -0.96
     salonu
    -0.91
    醍
    -0.91
     tutup
    -0.90
    chuhe
    -0.88
     ов
    -0.87
    POSITIVE LOGITS
    āya
    1.02
    com
    1.01
    +"
    1.00
    springframework
    0.99
    </h2>
    0.97
    ค
    0.93
    ()<<
    0.93
     quoque
    0.93
    $\$
    0.92
    激光
    0.89
    Activations Density 0.040%

    No Known Activations