© 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. 34-GEMMASCOPE-RES-131K
    7. 99960
    Prev
    Next
    INDEX
    Explanations

    header include statements

    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
    ESTRE
    -0.85
    стандарт
    -0.79
    umpulan
    -0.76
     aufgestellt
    -0.75
    tratamiento
    -0.75
     idag
    -0.74
     หล
    -0.74
    ohjel
    -0.74
    ロー
    -0.73
     ē
    -0.73
    POSITIVE LOGITS
     render
    0.84
    rindo
    0.80
     reseller
    0.79
    Ń
    0.78
     цей
    0.75
     crocodiles
    0.75
    render
    0.75
     robbers
    0.75
     IOM
    0.74
     rendering
    0.73
    Activations Density 0.001%

    No Known Activations