© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44334
    Prev
    Next
    INDEX
    Explanations

    philippines

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

    The neuron strongly activates on mentions of “Philippines” (and its major island regions such as Luzon, Visayas, Mindanao), i.e. geographic references to the Philippines.

    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
    0
    -3.64
    8
    -2.45
     ).
    -2.34
    y
    -2.34
     to
    -2.28
     --
    -2.27
     четырех
    -2.25
    gefügt
    -2.25
    9
    -2.22
    1
    -2.16
    POSITIVE LOGITS
     saveiro
    2.63
    鹟
    2.56
     Temporada
    2.31
     Jogo
    2.23
    鮃
    2.23
     médias
    2.22
    /−
    2.19
    鿬
    2.17
    viembre
    2.14
    菹
    2.13
    Activations Density 0.005%

    No Known Activations