© 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. 108347
    Prev
    Next
    INDEX
    Explanations

    dri followed by certain endings

    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
    masti
    -0.75
    tudiant
    -0.72
     Remembrance
    -0.71
     hết
    -0.70
     wrongdoing
    -0.70
    7
    -0.70
     الغذ
    -0.69
     Fact
    -0.67
     single
    -0.67
     calme
    -0.66
    POSITIVE LOGITS
     dri
    1.27
     Dri
    1.21
    Dri
    1.13
    ета
    0.93
    dri
    0.93
     Chỉ
    0.90
    ドリ
    0.89
     Глав
    0.85
     egyszer
    0.85
    meia
    0.79
    Activations Density 0.012%

    No Known Activations