© 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. 79559
    Prev
    Next
    INDEX
    Explanations

    parts and sections

    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
    様々
    -0.85
     spou
    -0.81
     poszczegól
    -0.81
    各类
    -0.81
     different
    -0.81
    多少钱
    -0.81
     recent
    -0.80
     everything
    -0.79
    atı
    -0.79
    íny
    -0.78
    POSITIVE LOGITS
     három
    1.08
     två
    1.01
     négy
    0.98
    part
    0.92
     מתוך
    0.91
     of
    0.88
    之一
    0.84
    sai
    0.83
    ertas
    0.83
     naturaleza
    0.82
    Activations Density 0.067%

    No Known Activations