© 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. 73412
    Prev
    Next
    INDEX
    Explanations

    George followed by Thomas

    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
     beruht
    -0.73
     explored
    -0.73
     actually
    -0.72
     Castilla
    -0.70
     wanting
    -0.69
    шення
    -0.69
     trận
    -0.69
    랄
    -0.68
     Доб
    -0.68
     tấn
    -0.67
    POSITIVE LOGITS
    Grath
    0.80
    UGHS
    0.77
    ��������
    0.75
     maverick
    0.75
    cans
    0.73
    üme
    0.73
    テニス
    0.72
    ),),
    0.72
    kultur
    0.71
    tttt
    0.71
    Activations Density 0.018%

    No Known Activations