© 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. 76466
    Prev
    Next
    INDEX
    Explanations

    美女主播, patient safety, 湖北

    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
    了一会儿
    -1.02
     ano
    -1.01
    hire
    -0.99
    冨
    -0.97
    mets
    -0.95
     psicológico
    -0.95
     saia
    -0.94
     palav
    -0.94
     hayat
    -0.93
    *************/
    -0.90
    POSITIVE LOGITS
    曾經
    1.02
     ofrecemos
    0.93
     跳转至
    0.90
    ولايات
    0.89
     obser
    0.88
    名稱
    0.84
    weightedMode
    0.84
    ően
    0.83
    asanjo
    0.83
     Reviewer
    0.82
    Activations Density 0.007%

    No Known Activations