© 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. 10-GEMMASCOPE-RES-131K
    7. 58305
    Prev
    Next
    INDEX
    Explanations

    countries and regions

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

    The neuron strongly activates on geographic place names (especially country names and other regions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     to
    -1.44
     your
    -1.23
     things
    -1.22
     ingredienti
    -1.16
     their
    -1.13
     now
    -1.13
     sogni
    -1.13
    หรือ
    -1.12
    :`
    -1.09
     legale
    -1.09
    POSITIVE LOGITS
     также
    1.57
     również
    1.52
     نیز
    1.45
     também
    1.41
    audiovisuel
    1.41
    asantry
    1.38
     également
    1.34
     acrylique
    1.31
     Also
    1.30
    Also
    1.30
    Activations Density 0.053%

    No Known Activations