© 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. 34-GEMMASCOPE-RES-131K
    7. 98845
    Prev
    Next
    INDEX
    Explanations

    mapping streets and maps

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

    The neuron specializes in spotting quantitative details—numerical expressions, measurements, counts, or coordinates—in the text.

    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
    "}";
    -1.21
    elux
    -1.03
    Netherlands
    -1.03
     Ostat
    -1.01
     típus
    -0.98
    okolade
    -0.97
    tellung
    -0.97
    nelt
    -0.96
    slant
    -0.95
     zabez
    -0.95
    POSITIVE LOGITS
     map
    2.03
     maps
    1.84
     zoom
    1.55
     zoomed
    1.41
     plotted
    1.41
    map
    1.38
     carto
    1.36
    zoom
    1.34
     depicting
    1.31
     mapped
    1.29
    Activations Density 0.055%

    No Known Activations