© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98243
    Prev
    Next
    INDEX
    Explanations

    numbers and code locations

    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_22/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
    Consejo
    -0.99
    Artículos
    -0.99
     свободы
    -0.91
     moky
    -0.91
    cepatan
    -0.91
     pasaran
    -0.90
    seda
    -0.88
    clairage
    -0.88
    obach
    -0.87
    Algemeen
    -0.87
    POSITIVE LOGITS
     such
    0.91
    ichert
    0.86
     members
    0.83
    .”)
    0.82
     łaz
    0.82
     れる
    0.82
     Hume
    0.82
    าร
    0.81
     virtud
    0.81
     Есть
    0.79
    Activations Density 0.021%

    No Known Activations