© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34825
    Prev
    Next
    INDEX
    Explanations

    spatial relationships and connections

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

    The neuron detects words and phrases that describe spatial relationships or positioning (e.g. place of, disposed opposite to, placed behind, stacked on top of).

    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
     flexibilidad
    -1.01
    madam
    -0.94
    ^{+
    -0.93
     mehreren
    -0.93
    ('/:
    -0.91
     numerosas
    -0.90
     desenli
    -0.90
     mantend
    -0.90
     zahlreichen
    -0.90
    ătate
    -0.90
    POSITIVE LOGITS
    same
    1.06
     same
    1.02
    ⬆
    0.91
     urbana
    0.85
    同じ
    0.82
    getNext
    0.82
    SAME
    0.82
    ordnet
    0.82
    next
    0.81
    同样
    0.81
    Activations Density 0.084%

    No Known Activations