© 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. 10-GEMMASCOPE-RES-131K
    7. 123672
    Prev
    Next
    INDEX
    Explanations

    grid layout

    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_10/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
    ↵↵
    -1.80
    ейчас
    -1.55
    Ꮉ
    -1.52
     Glaube
    -1.52
     概要
    -1.52
    řízení
    -1.50
     ДЕ
    -1.45
    ваться
    -1.44
    אין
    -1.41
    tlement
    -1.39
    POSITIVE LOGITS
    ?
    1.95
    "
    1.75
     pourrait
    1.41
     kies
    1.41
     '
    1.40
    )
    1.36
    ("
    1.34
    蟊
    1.34
    —
    1.33
     centrales
    1.32
    Activations Density 0.014%

    No Known Activations