© 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. 15647
    Prev
    Next
    INDEX
    Explanations

    why 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
    When
    -2.00
     what
    -1.73
    What
    -1.72
     When
    -1.72
    Once
    -1.65
     when
    -1.64
    Before
    -1.63
    If
    -1.62
    One
    -1.55
    It
    -1.53
    POSITIVE LOGITS
     achats
    1.55
     lakini
    1.38
     fm
    1.31
     verminder
    1.27
     navires
    1.27
     oa
    1.26
     curent
    1.25
     ftp
    1.24
     werkt
    1.23
     prochains
    1.23
    Activations Density 0.043%

    No Known Activations