© 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. 9313
    Prev
    Next
    INDEX
    Explanations

    programming operators and operands

    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
    shadowOpacity
    -1.06
    økt
    -1.05
    columnwidth
    -0.95
    颔
    -0.94
    cets
    -0.94
     Geruch
    -0.92
     Befe
    -0.91
    rento
    -0.90
    阳台
    -0.90
     level
    -0.90
    POSITIVE LOGITS
     we
    1.30
     norvég
    1.00
     gelar
    1.00
     keramik
    0.94
     tumbuhan
    0.93
    ллю
    0.93
     pembelajaran
    0.92
    诧
    0.92
     bordir
    0.92
     편
    0.91
    Activations Density 0.007%

    No Known Activations