© 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. 34-GEMMASCOPE-RES-131K
    7. 103611
    Prev
    Next
    INDEX
    Explanations

    Python API and code structures

    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
    lanze
    -0.75
    UALLY
    -0.75
    verride
    -0.75
     where
    -0.72
     Seelen
    -0.70
     electrico
    -0.70
    おきます
    -0.69
     oculto
    -0.69
    uva
    -0.68
    яр
    -0.68
    POSITIVE LOGITS
     Allegheny
    1.09
    Pennsylvania
    0.88
     изменений
    0.83
     مانت
    0.82
    {})
    0.82
    〖
    0.79
     VMware
    0.79
     Pennsylvania
    0.79
    údos
    0.79
    ᐊ
    0.78
    Activations Density 0.003%

    No Known Activations