© 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. 45261
    Prev
    Next
    INDEX
    Explanations

    sports draft

    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
    ckså
    -0.74
    Inter
    -0.72
    nic
    -0.71
     门
    -0.71
    INTR
    -0.69
    LIBR
    -0.69
     hellen
    -0.69
    NIC
    -0.66
     Heater
    -0.66
    なこと
    -0.66
    POSITIVE LOGITS
    QtGui
    0.87
     drafting
    0.87
     julio
    0.84
     draft
    0.82
    CED
    0.80
    ulica
    0.78
     julho
    0.77
    tachten
    0.76
    天才
    0.75
     souris
    0.75
    Activations Density 0.027%

    No Known Activations