© 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. 79406
    Prev
    Next
    INDEX
    Explanations

    word beginnings and their continuations

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on chunks of proper place names (geographical location names).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    торая
    -0.96
    cambios
    -0.93
    reszcie
    -0.92
    znám
    -0.91
    quels
    -0.91
    iis
    -0.90
     zestawie
    -0.90
     końcu
    -0.90
    moet
    -0.90
     sprawie
    -0.88
    POSITIVE LOGITS
    owaniu
    1.09
    uyasha
    0.98
    bihan
    0.96
     sudah
    0.90
    !!.
    0.90
    oldown
    0.87
    xique
    0.87
    énario
    0.86
    bulin
    0.86
    issement
    0.86
    Activations Density 0.021%

    No Known Activations