© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33693
    Prev
    Next
    INDEX
    Explanations

    email)Do youCathedralColeophoraQ:

    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
     NCERT
    -0.78
     whose
    -0.77
     чле
    -0.75
     Montenegro
    -0.74
     meninggal
    -0.74
     iload
    -0.73
     Ginn
    -0.73
     palaces
    -0.73
    oureux
    -0.72
    palace
    -0.72
    POSITIVE LOGITS
    救援
    0.87
     νέ
    0.84
    ján
    0.83
     klin
    0.82
     infek
    0.81
    OCUS
    0.80
    utu
    0.78
     تا
    0.78
     Bart
    0.77
     nasel
    0.76
    Activations Density 0.000%

    No Known Activations