© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 47429
    Prev
    Next
    INDEX
    Explanations

    last names jones doe smith

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ＠
    0.46
     Oscars
    0.44
     Gub
    0.44
    '@
    0.42
     MNIST
    0.41
     WordPerfect
    0.41
    蟒
    0.41
     "@
    0.41
     Vanity
    0.41
     Betfair
    0.41
    POSITIVE LOGITS
    a
    0.65
    ag
    0.47
    arthen
    0.45
    jackson
    0.45
    agency
    0.44
    ask
    0.43
    fact
    0.42
    i
    0.42
    phone
    0.41
    employee
    0.41
    Activations Density 0.007%

    No Known Activations