© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 114001
    Prev
    Next
    INDEX
    Explanations

    past participles after 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
    Negative Logits
    p
    -2.06
    c
    -1.90
     但是
    -1.81
    s
    -1.74
    ではでは
    -1.73
    ons
    -1.66
    4
    -1.66
    t
    -1.63
     都
    -1.61
     我们
    -1.61
    POSITIVE LOGITS
     revelado
    1.98
     adquirido
    1.84
     explicado
    1.82
     comprado
    1.77
     jugado
    1.75
     conseguido
    1.73
     destacado
    1.70
     anunciado
    1.66
     atacado
    1.66
    >]
    1.63
    Activations Density 0.047%

    No Known Activations