© 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. 118530
    Prev
    Next
    INDEX
    Explanations

    accompanying someone or something

    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
     Interaction
    -0.88
     Interactions
    -0.77
    ्त
    -0.77
    ienza
    -0.73
    Interaction
    -0.73
     entrevist
    -0.73
     dosta
    -0.72
     взаимо
    -0.71
     subray
    -0.70
    interaction
    -0.70
    POSITIVE LOGITS
     accompany
    4.22
     accompanies
    3.55
     accompanying
    3.33
     tagging
    3.00
     همراه
    2.77
     tag
    2.77
     acompañ
    2.69
     accompaniment
    2.67
     accompanied
    2.61
     сопрово
    2.61
    Activations Density 0.066%

    No Known Activations