© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91894
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure

    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
    izzera
    -0.90
     vicente
    -0.88
    heater
    -0.81
     giorgio
    -0.81
     milano
    -0.81
    printable
    -0.81
    لفة
    -0.80
     gigi
    -0.80
     suzuki
    -0.80
    mappedBy
    -0.79
    POSITIVE LOGITS
     dancer
    0.85
     مساء
    0.84
     epic
    0.79
     alegría
    0.79
     någon
    0.78
     chrome
    0.77
     kings
    0.75
     Nile
    0.74
     الخم
    0.71
    urd
    0.70
    Activations Density 0.000%

    No Known Activations