© 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. 92486
    Prev
    Next
    INDEX
    Explanations

    Crabb, Bransgore, Broaddus, Brauer, Frykman, Cremer, Dreelen

    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
    varphi
    -0.91
    һы
    -0.83
     comet
    -0.81
    Cohen
    -0.80
     поверх
    -0.77
     nanotubes
    -0.77
    itology
    -0.75
     hukuman
    -0.75
    Stu
    -0.74
    nanoTime
    -0.74
    POSITIVE LOGITS
     brano
    1.03
     Creighton
    0.99
     Hra
    0.97
     Zheng
    0.95
     crate
    0.94
     크
    0.94
     kred
    0.93
    Grath
    0.92
     credit
    0.91
     бра
    0.90
    Activations Density 0.061%

    No Known Activations