© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 80062
    Prev
    Next
    INDEX
    Explanations

    GIS, GPS, mapping, and navigation

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

    The neuron fires strongly on geospatial acronyms and technical terms (e.g. “GIS,” “GPS,” “projected spaces,” “ArcGIS,” etc.), i.e. references to geographic information and positioning systems.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     "");
    -1.35
    ₂)
    -1.20
     Voltage
    -1.20
    𝓚
    -1.19
     elegido
    -1.19
    (",")
    -1.19
    ,:),
    -1.18
     Rumuni
    -1.14
     Wię
    -1.14
    ₁)
    -1.14
    POSITIVE LOGITS
     map
    1.14
     accuracy
    1.13
    3
    1.13
     results
    1.12
     data
    1.12
    map
    1.08
     掃除
    1.05
     pajero
    1.05
    urances
    1.03
     mapper
    1.02
    Activations Density 0.106%

    No Known Activations