© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 37924
    Prev
    Next
    INDEX
    Explanations

    numbers and names

    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
     family
    -2.09
    family
    -1.75
     FAMILY
    -1.48
     Family
    -1.47
    Family
    -1.42
     familia
    -1.38
    FAMILY
    -1.35
     Familie
    -1.33
     família
    -1.30
     famille
    -1.23
    POSITIVE LOGITS
    бовал
    0.76
     Kindergarten
    0.74
    baran
    0.73
    ispo
    0.72
    Crack
    0.71
    Servlet
    0.71
     tactile
    0.71
    ranks
    0.70
    СКО
    0.69
    šas
    0.68
    Activations Density 0.040%

    No Known Activations