© 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. 107696
    Prev
    Next
    INDEX
    Explanations

    arrest warrant, wearing clothes, program titles, question headings

    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
    ritsar
    -0.81
     triko
    -0.81
    Chile
    -0.79
    callable
    -0.78
     geri
    -0.76
     Gry
    -0.76
     Gi
    -0.75
     çünkü
    -0.73
     جز
    -0.73
    不由得
    -0.73
    POSITIVE LOGITS
     paraffin
    0.92
    buy
    0.85
     buy
    0.79
     hotly
    0.79
     medico
    0.78
    ᄐ
    0.78
     prompting
    0.78
     sprigs
    0.77
     recuperación
    0.77
     integrada
    0.76
    Activations Density 0.004%

    No Known Activations