© 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. 66184
    Prev
    Next
    INDEX
    Explanations

    spatial relationships

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

    The neuron detects phrases that express spatial adjacency or proximity (e.g. “adjacent to,” “directly behind,” “above”).

    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
     ทั้ง
    -1.00
    作为一个
    -0.99
    把他
    -0.96
    selbe
    -0.94
    ViewFeatures
    -0.93
    dhism
    -0.91
    上下
    -0.91
    ͋
    -0.90
    事情
    -0.90
    Ótimo
    -0.86
    POSITIVE LOGITS
     the
    2.16
     immédi
    1.50
     and
    1.45
     or
    1.41
     them
    1.33
     where
    1.28
     each
    1.19
    neath
    1.11
     مباشرة
    1.09
     eachother
    1.07
    Activations Density 0.078%

    No Known Activations