© 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. 103858
    Prev
    Next
    INDEX
    Explanations

    subjects and education

    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
    orist
    -0.79
     tradução
    -0.78
     menit
    -0.77
    メソッド
    -0.76
    久しぶりに
    -0.75
    Алексей
    -0.74
     formen
    -0.72
    isuke
    -0.71
    remadura
    -0.71
     philippe
    -0.71
    POSITIVE LOGITS
     biology
    3.20
     physics
    3.20
     math
    3.06
     chemistry
    2.98
     mathematics
    2.92
     maths
    2.91
     Biology
    2.89
     Physics
    2.78
     Chemistry
    2.72
     Mathematics
    2.66
    Activations Density 0.143%

    No Known Activations