© 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. 38443
    Prev
    Next
    INDEX
    Explanations

    punctuation and conditional words

    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
    0
    -1.96
     
    -1.95
    "
    -1.92
     этих
    -1.91
     You
    -1.69
     его
    -1.68
     votre
    -1.59
    9
    -1.59
     otras
    -1.54
     этой
    -1.53
    POSITIVE LOGITS
     before
    1.91
     if
    1.86
     during
    1.84
    ୈ
    1.74
    狃
    1.69
     where
    1.68
     when
    1.66
     as
    1.65
     without
    1.63
     although
    1.60
    Activations Density 0.013%

    No Known Activations