© 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. 22-GEMMASCOPE-RES-131K
    7. 98483
    Prev
    Next
    INDEX
    Explanations

    citing sources and attributions

    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_22/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
     그것
    -0.98
     '*',
    -0.96
    ẨM
    -0.96
     {},
    -0.95
     '/',
    -0.94
    dillera
    -0.93
     autrement
    -0.93
     古着
    -0.93
    〛
    -0.93
    ništvo
    -0.92
    POSITIVE LOGITS
     "
    1.38
     only
    1.30
    邉
    1.04
     "...
    1.03
     turísticos
    1.01
     “
    1.01
     azért
    0.96
     currently
    0.96
    }{||
    0.95
    kunjung
    0.95
    Activations Density 0.051%

    No Known Activations