© 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. 56905
    Prev
    Next
    INDEX
    Explanations

    age-matched comparisons

    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
     Jag
    -0.79
    Jag
    -0.77
     Desired
    -0.72
     Rockstar
    -0.70
    FirstName
    -0.69
    Asu
    -0.69
    lico
    -0.67
    krishnan
    -0.67
    czeń
    -0.67
    Mak
    -0.66
    POSITIVE LOGITS
     matched
    5.47
    matched
    4.75
    Matched
    4.19
     matching
    3.61
     match
    3.33
     Matching
    3.19
    matching
    3.08
    匹配
    3.06
    match
    2.98
    Matching
    2.95
    Activations Density 0.201%

    No Known Activations