© 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. 34751
    Prev
    Next
    INDEX
    Explanations

    questions and definitions

    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
     suceso
    -0.81
     neum
    -0.80
     asesinato
    -0.79
     respetar
    -0.79
     adoptar
    -0.78
    ؔ
    -0.76
    ロリ
    -0.75
    emporio
    -0.75
    Oltre
    -0.74
     düğün
    -0.73
    POSITIVE LOGITS
     Wikidata
    0.73
     фе
    0.72
    HIDE
    0.71
    اظ
    0.70
     CONSIDER
    0.69
     मामले
    0.69
     huella
    0.69
    loroethene
    0.69
     republic
    0.68
    átky
    0.68
    Activations Density 0.000%

    No Known Activations