© 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. 34-GEMMASCOPE-RES-131K
    4. 118160
    Prev
    Next
    INDEX
    Explanations

    followed by "to"

    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_34/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
     capucha
    -2.17
     almohada
    -1.95
     cojín
    -1.85
     tirantes
    -1.84
     bañera
    -1.82
     lentejuelas
    -1.80
     macetas
    -1.70
     sandalias
    -1.70
     maceta
    -1.69
     mascarilla
    -1.68
    POSITIVE LOGITS
     to
    10.56
     To
    3.38
    to
    3.13
    To
    2.94
    到
    2.69
     إلى
    2.67
     TO
    2.03
     đến
    2.03
     به
    2.02
    DataTo
    1.89
    Activations Density 0.204%

    No Known Activations