© 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. 68745
    Prev
    Next
    INDEX
    Explanations

    Suffolk, Ipswich, Flanders

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

    The neuron activates on named geographic locations.

    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
    ?”
    -3.31
     сделал
    -2.55
     But
    -2.55
     usada
    -2.45
     делает
    -2.42
     sabias
    -2.42
    眥
    -2.39
     maravillosas
    -2.33
    ...”
    -2.31
    VNB
    -2.30
    POSITIVE LOGITS
    the
    2.67
    2
    2.64
    they
    2.53
    ?
    2.39
    ',
    2.36
    V
    2.34
    $
    2.33
    횃
    2.14
    Ꭳ
    2.14
    alties
    2.06
    Activations Density 0.003%

    No Known Activations