© 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. 34-GEMMASCOPE-RES-131K
    4. 75988
    Prev
    Next
    INDEX
    Explanations

    distance from places

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

    The neuron flags mentions of specific geographic distances or directional location measures (e.g. “35 kilometres northwest of Downtown” or “22 kilometres south‐west of the Sydney central business district”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     augmente
    -0.90
     cooperativa
    -0.86
    llllllll
    -0.86
    lunda
    -0.85
    直播间
    -0.85
    ̔
    -0.85
     rece
    -0.84
    加拿
    -0.84
    !='
    -0.83
     doña
    -0.82
    POSITIVE LOGITS
     workplace
    1.18
     workplaces
    1.16
     office
    1.04
     city
    0.97
     werken
    0.96
     workday
    0.96
     where
    0.94
     employment
    0.93
     employer
    0.91
    Instruments
    0.88
    Activations Density 0.002%

    No Known Activations