© 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. 1323
    Prev
    Next
    INDEX
    Explanations

    Osijek, Kasiisi, Wasikowska

    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
    轻
    -0.78
    َب
    -0.75
    新品
    -0.74
    منى
    -0.70
    CTOR
    -0.68
    松
    -0.68
    ஷ
    -0.66
     Бел
    -0.66
    rale
    -0.66
     pestaña
    -0.65
    POSITIVE LOGITS
    ューズ
    0.93
    oughlin
    0.81
     ermöglicht
    0.77
     ASI
    0.77
    衿
    0.77
    ApiRequest
    0.76
     semiconductors
    0.73
    tmp
    0.73
    Alli
    0.73
    lac
    0.72
    Activations Density 0.039%

    No Known Activations