© 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. 128868
    Prev
    Next
    INDEX
    Explanations

    places and relatives

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

    This neuron specializes in picking out mentions of physical locations or places where people or items are situated.

    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
    anadium
    -1.37
    imee
    -1.20
    nemia
    -1.20
    lossene
    -1.14
     játék
    -1.12
    uyasha
    -1.11
    рест
    -1.09
    sworth
    -1.07
    vaila
    -1.06
     maquilla
    -1.06
    POSITIVE LOGITS
     sogar
    1.26
     them
    1.25
     dankbar
    1.19
    uffff
    1.17
    It
    1.15
    raktion
    1.14
     його
    1.13
     время
    1.13
     nawet
    1.09
    endiri
    1.09
    Activations Density 0.180%

    No Known Activations