© 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. 12657
    Prev
    Next
    INDEX
    Explanations

    programming variable assignments and operations

    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
     寿
    -1.07
     extrême
    -0.97
    ᴘ
    -0.96
     you
    -0.89
     heridas
    -0.88
    Liquidity
    -0.87
    高温
    -0.87
    Ŭ
    -0.86
    ckeys
    -0.86
    الا
    -0.85
    POSITIVE LOGITS
     we
    0.84
    Какие
    0.82
     trés
    0.80
     می‌کن
    0.77
    Здра
    0.76
     corrobor
    0.76
    sometimes
    0.76
    Опыт
    0.75
     then
    0.75
    是个
    0.75
    Activations Density 0.010%

    No Known Activations