© 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. 10-GEMMASCOPE-RES-131K
    7. 68932
    Prev
    Next
    INDEX
    Explanations

    code comments and documentation

    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_10/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
     to
    -1.77
     this
    -1.76
    1
    -1.53
    vedades
    -1.49
    tą
    -1.48
    2
    -1.47
     like
    -1.41
     animación
    -1.26
    3
    -1.25
    毟
    -1.20
    POSITIVE LOGITS
    ཫ
    1.53
    随着
    1.45
     modernas
    1.42
    Én
    1.39
    komna
    1.38
    maktadır
    1.34
    我没有
    1.34
    kém
    1.33
    leyici
    1.33
    cepatan
    1.33
    Activations Density 0.006%

    No Known Activations