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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31906
    Prev
    Next
    INDEX
    Explanations

    nomadic groups, travellers, gypsies

    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
     terr
    -0.88
     maso
    -0.77
     russ
    -0.77
     Tartu
    -0.74
     گر
    -0.73
     Corrosion
    -0.73
    égio
    -0.73
     corrupt
    -0.72
     fap
    -0.71
    ilíbrio
    -0.71
    POSITIVE LOGITS
     encampment
    1.23
     traveller
    1.04
     Traveller
    0.96
     Travelling
    0.91
    remoto
    0.91
    trav
    0.90
     site
    0.89
    plish
    0.89
    Sites
    0.89
     nomadic
    0.89
    Activations Density 0.004%

    No Known Activations