© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11962
    Prev
    Next
    INDEX
    Explanations

    contracts and agreements

    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
     have
    -1.50
    щи
    -1.34
    凩
    -1.33
    ㍑
    -1.31
    來
    -1.31
    Carthy
    -1.28
     who
    -1.27
    вого
    -1.25
    ativement
    -1.23
    HXLINE
    -1.22
    POSITIVE LOGITS
     that
    2.09
     inoxidable
    1.39
     interesado
    1.29
     contract
    1.27
     plazos
    1.26
     itself
    1.26
     pantalones
    1.25
     terms
    1.24
     playoff
    1.23
     känna
    1.23
    Activations Density 0.076%

    No Known Activations