© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13799
    Prev
    Next
    INDEX
    Explanations

    South America

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

    The neuron strongly activates on mentions of “South America” (including adjectival forms like “South American”).

    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
    5
    -2.89
    9
    -2.77
    8
    -2.64
    6
    -2.42
    from
    -2.31
    7
    -2.30
    We
    -2.20
    4
    -2.14
    ٞ
    -2.11
    ="
    -2.06
    POSITIVE LOGITS
     Hinblick
    1.89
     to
    1.87
     convenio
    1.79
     sólidos
    1.79
     of
    1.79
    ↵↵
    1.73
     are
    1.72
     parlak
    1.71
    迄
    1.70
    𐤔
    1.67
    Activations Density 0.011%

    No Known Activations