© 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. 98562
    Prev
    Next
    INDEX
    Explanations

    locations and distances

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

    The neuron fires strongly on numbers and associated measurement tokens (distances, times, counts) in location or property descriptions.

    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
    ັ
    -0.79
    出于
    -0.76
     vilket
    -0.74
     Kat
    -0.74
    точно
    -0.73
    velmente
    -0.73
     Soy
    -0.73
     graphics
    -0.73
    arean
    -0.73
     Пер
    -0.72
    POSITIVE LOGITS
    るか
    0.82
    Bains
    0.79
     streetwear
    0.77
    Vehicles
    0.75
    );?>
    0.75
    debit
    0.74
    NOAA
    0.74
     viande
    0.72
     Failures
    0.72
    rillas
    0.71
    Activations Density 0.010%

    No Known Activations