© 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. 103710
    Prev
    Next
    INDEX
    Explanations

    Bangalore city

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

    The neuron detects recurring mentions of a specific geographic place name.

    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
    \
    -3.30
    ed
    -3.02
     が
    -2.61
    "
    -2.61
    人の
    -2.53
    Your
    -2.52
     بالإضافة
    -2.50
    Our
    -2.45
     
    -2.45
    We
    -2.44
    POSITIVE LOGITS
    衚
    3.31
    珰
    2.89
    釤
    2.88
     verkau
    2.80
     zobac
    2.75
     gewähr
    2.69
     новом
    2.61
     использовании
    2.58
    搥
    2.58
     проведения
    2.53
    Activations Density 0.005%

    No Known Activations