© 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. 10-GEMMASCOPE-RES-131K
    7. 39644
    Prev
    Next
    INDEX
    Explanations

    Kenya, names, and places

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

    The neuron activates strongly on capitalized proper names (especially geographic locations and personal names).

    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
    ίες
    -1.63
    なー
    -1.57
    他现在
    -1.45
    这下
    -1.40
    ねー
    -1.38
    down
    -1.38
    ATELY
    -1.37
    ximadamente
    -1.36
    よくある
    -1.35
    ities
    -1.34
    POSITIVE LOGITS
     única
    1.49
    cknowledge
    1.48
    celtic
    1.46
    delic
    1.44
    tų
    1.39
     vínculo
    1.39
    california
    1.38
    dersfield
    1.37
    体重
    1.36
    ,''
    1.34
    Activations Density 0.005%

    No Known Activations