© 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. 66069
    Prev
    Next
    INDEX
    Explanations

    function definitions and loops

    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
    丰富的
    -0.90
    随便
    -0.82
     ugu
    -0.75
    groet
    -0.75
     Unicorn
    -0.75
    paquete
    -0.75
     classifica
    -0.74
     miniatura
    -0.74
    daftar
    -0.73
    Conexao
    -0.73
    POSITIVE LOGITS
     from
    1.09
     vanaf
    0.85
     between
    0.79
     there
    0.79
    文中
    0.73
     Mal
    0.71
     biomarkers
    0.69
    瞭
    0.69
    max
    0.69
     evacuate
    0.69
    Activations Density 0.015%

    No Known Activations