© 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. 68485
    Prev
    Next
    INDEX
    Explanations

    events following during

    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
     пусть
    -1.18
    ₩
    -1.12
     wtedy
    -1.08
    penup
    -1.07
     respetu
    -1.06
     Obtén
    -1.06
    getUser
    -1.05
     TÉCN
    -1.04
     лимон
    -1.04
    }`).
    -1.02
    POSITIVE LOGITS
     روسیه
    1.10
     udang
    1.10
    магази
    1.08
    nasional
    1.07
     ۱۴
    1.02
     for
    1.02
     utford
    0.98
     $
    0.95
     شناسی
    0.94
     katika
    0.94
    Activations Density 0.002%

    No Known Activations