© 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. 79254
    Prev
    Next
    INDEX
    Explanations

    mass, couplings, and energy scales

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ionage
    -0.80
    淸
    -0.76
     carriers
    -0.73
     getItemCount
    -0.73
    ennia
    -0.72
    hrens
    -0.71
    inkled
    -0.71
     мора
    -0.70
    疑
    -0.69
     threaten
    -0.69
    POSITIVE LOGITS
     mass
    0.78
     couplings
    0.78
     rapports
    0.78
     masa
    0.76
    mass
    0.75
     Liss
    0.73
    weigh
    0.73
     g
    0.72
     Mass
    0.71
     coupling
    0.70
    Activations Density 0.013%

    No Known Activations