© 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. 68466
    Prev
    Next
    INDEX
    Explanations

    references, bibliography, external links

    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
     récord
    -1.06
    Переваги
    -1.04
    According
    -1.02
     nowej
    -1.02
     url
    -0.99
     grosir
    -0.99
    再び
    -0.98
    イルミネ
    -0.98
    =$((
    -0.97
     |
    -0.95
    POSITIVE LOGITS
    MIDDLEWARE
    1.17
     klokken
    1.11
    oczes
    1.10
     akong
    1.05
    либо
    1.03
    대한
    1.02
    <bos>
    1.02
     toimi
    1.02
     norske
    1.01
     kirjo
    1.00
    Activations Density 0.003%

    No Known Activations