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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71298
    Prev
    Next
    INDEX
    Explanations

    location prepositions

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

    The neuron fires strongly on spatial prepositions (like “inside,” “outside,” or “above”) that introduce or accompany numeric or quantitative descriptions of location.

    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
     entornos
    -1.52
     versátil
    -1.49
     paisagem
    -1.49
     эти
    -1.45
    问我
    -1.44
     cómodo
    -1.42
     мы
    -1.41
    告诉我
    -1.38
     extracción
    -1.35
     meditación
    -1.35
    POSITIVE LOGITS
     for
    2.19
     about
    1.77
     to
    1.74
     in
    1.70
    2
    1.58
     into
    1.56
     from
    1.48
    C
    1.44
     کردند
    1.40
    N
    1.40
    Activations Density 0.051%

    No Known Activations