© 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. 7260
    Prev
    Next
    INDEX
    Explanations

    educational materials and 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
     serán
    -0.81
    ܦ
    -0.75
    ColumnInfo
    -0.72
     Anja
    -0.71
     tenemos
    -0.68
    lottesville
    -0.67
    asaan
    -0.66
    irat
    -0.66
    毫
    -0.66
    śnie
    -0.65
    POSITIVE LOGITS
     syndromes
    0.78
    Produktion
    0.78
    用語
    0.74
     production
    0.73
    полу
    0.73
    ステル
    0.72
    Espèce
    0.71
     は
    0.71
    ماعة
    0.71
     допуска
    0.71
    Activations Density 0.008%

    No Known Activations