© 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. 48199
    Prev
    Next
    INDEX
    Explanations

    to + action verbs

    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
     aislados
    -2.03
     dispuestos
    -1.87
     cubiertos
    -1.70
     listos
    -1.70
     animados
    -1.66
     preparados
    -1.66
     abiertos
    -1.65
    絝
    -1.63
    medriver
    -1.63
     exitosa
    -1.59
    POSITIVE LOGITS
    When
    1.79
    нами
    1.59
    檠
    1.53
     berpikir
    1.53
    涷
    1.51
     berkenaan
    1.50
    婓
    1.44
    лимпи
    1.43
     號
    1.41
     tages
    1.41
    Activations Density 0.092%

    No Known Activations