© 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. 15730
    Prev
    Next
    INDEX
    Explanations

    Tanzania and Norfolk

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

    The neuron responds to mentions of the country name “Tanzania.”

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    縢
    -3.08
     Importantly
    -2.72
     Within
    -2.66
     Notwithstanding
    -2.64
    ers
    -2.58
     This
    -2.56
     Evidently
    -2.42
    鸲
    -2.41
    á
    -2.41
     Whilst
    -2.41
    POSITIVE LOGITS
    ↵↵
    2.89
    驁
    2.23
     were
    2.22
    憮
    2.22
     необы
    2.20
     remainder
    2.16
    鼇
    2.14
    蟶
    2.13
     был
    2.11
     男人
    2.11
    Activations Density 0.003%

    No Known Activations