© 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. 58411
    Prev
    Next
    INDEX
    Explanations

    Philippines entities and contexts

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

    The neuron activates on capitalized named entities, especially geographic locations and organization or person 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
     īpa
    -1.24
     воздействия
    -1.18
    kespeare
    -1.16
     tersebut
    -1.14
     cilvē
    -1.08
    andte
    -1.07
     viņ
    -1.05
    こいつ
    -1.02
    uchtet
    -1.02
    气质
    -1.00
    POSITIVE LOGITS
     to
    1.44
    菲律
    1.24
     my
    1.14
     difund
    1.13
    
    1.02
    ufficient
    1.01
     ilustracji
    0.98
    what
    0.98
     any
    0.96
    BERTO
    0.94
    Activations Density 0.083%

    No Known Activations