© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73675
    Prev
    Next
    INDEX
    Explanations

    verbs meaning "to be" and definitions

    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
    噐
    -2.66
    錞
    -2.63
    ーズン
    -2.61
    沨
    -2.58
     北市
    -2.55
     твои
    -2.53
    檯
    -2.53
     DÍA
    -2.52
    
    -2.44
    寕
    -2.44
    POSITIVE LOGITS
     able
    2.84
     regarded
    2.59
     a
    2.39
     termed
    2.34
    ’
    2.20
     “
    2.16
     viewed
    2.16
     comprised
    2.11
    (
    2.09
     called
    2.06
    Activations Density 0.001%

    No Known Activations