© 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. 36
    Prev
    Next
    INDEX
    Explanations

    mathematical and code syntax

    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
    _
    -2.20
    Симпто
    -1.34
     після
    -1.27
     still
    -1.27
     encontre
    -1.23
     poate
    -1.23
    鑷
    -1.22
    __
    -1.21
    及び
    -1.20
     excluir
    -1.20
    POSITIVE LOGITS
    越好
    1.41
    LLABLE
    1.38
    trino
    1.36
    鞴
    1.36
    ÇÃO
    1.35
     olika
    1.34
    ize
    1.34
    nellement
    1.34
    هایی
    1.32
    zości
    1.32
    Activations Density 0.037%

    No Known Activations