© 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. 29882
    Prev
    Next
    INDEX
    Explanations

    Homology and functors

    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
     event
    -0.79
     Ideen
    -0.77
     Download
    -0.75
    kne
    -0.74
     kejadian
    -0.71
     Coulomb
    -0.71
    strokeWeight
    -0.71
     DOWNLOAD
    -0.71
    Event
    -0.71
     Event
    -0.70
    POSITIVE LOGITS
     Hom
    1.34
    Hom
    1.33
     hom
    1.08
     functor
    1.07
    hom
    1.03
     HOM
    0.89
     (-)
    0.81
     homology
    0.81
    (-)
    0.76
     postfix
    0.75
    Activations Density 0.032%

    No Known Activations