© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99600
    Prev
    Next
    INDEX
    Explanations

    Mohawk Valley, Piedmont Region, Melton Mowbray

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

    The neuron detects mentions of specific geographic region names (e.g. “Mohawk,” “Piedmont,” “Melton Mowbray”).

    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
    闥
    -2.98
    èvent
    -2.67
     Handlungen
    -2.66
     でも
    -2.45
    骓
    -2.39
    大爷
    -2.30
    一说
    -2.23
     Einrichtungen
    -2.22
    栒
    -2.19
     Situationen
    -2.16
    POSITIVE LOGITS
    z
    2.77
    没
    2.66
    at
    2.66
    并没有
    2.56
     Your
    2.52
    Ꮞ
    2.50
    ↵
    2.41
    K
    2.39
    t
    2.36
     ''
    2.31
    Activations Density 0.013%

    No Known Activations