© 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. 34-GEMMASCOPE-RES-131K
    7. 94224
    Prev
    Next
    INDEX
    Explanations

    numbers and years

    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
    Negative Logits
    obes
    -0.73
     ۷
    -0.73
     mög
    -0.71
     Stre
    -0.68
     extr
    -0.67
    ⑼
    -0.67
    нах
    -0.65
     intercept
    -0.64
    æn
    -0.64
     REV
    -0.64
    POSITIVE LOGITS
     eighteen
    2.09
     Eighteen
    1.99
     nineteen
    1.70
     eighteenth
    1.63
    十八
    1.56
     ۱۸
    1.56
     teenager
    1.48
     Nineteen
    1.48
     XVIII
    1.47
     nineteenth
    1.45
    Activations Density 0.062%

    No Known Activations