© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48759
    Prev
    Next
    INDEX
    Explanations

    place names and geographical locations

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

    The neuron fires on place‐ and region‐names (geographical proper nouns) in encyclopedic‐style text.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Hora
    -0.77
     Waterloo
    -0.75
     Mannheim
    -0.74
     страну
    -0.72
    ⣼
    -0.71
     skjø
    -0.71
     XXVII
    -0.70
     осте
    -0.69
     XXVIII
    -0.69
     Delo
    -0.68
    POSITIVE LOGITS
     Chhattisgarh
    0.91
     Chiapas
    0.84
     ESS
    0.79
    pillar
    0.77
     Ess
    0.76
     Shasta
    0.73
     initWith
    0.71
     equal
    0.71
     Bourke
    0.70
    bilisi
    0.69
    Activations Density 0.034%

    No Known Activations