© 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. 34-GEMMASCOPE-RES-131K
    7. 116240
    Prev
    Next
    INDEX
    Explanations

    directional prepositions and spatial relationships

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

    This neuron detects the “obl” sequence marking oblique dependency labels (i.e. occurrences of the UD “obl” relation).

    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
    Known
    -0.77
    oramic
    -0.73
    KNOWN
    -0.73
    kování
    -0.72
    unc
    -0.72
     furono
    -0.71
     agarre
    -0.71
     صفر
    -0.71
    꼴
    -0.70
    keren
    -0.69
    POSITIVE LOGITS
     preposition
    1.98
    介
    1.15
     spatial
    1.05
     Prep
    1.03
     prep
    1.03
     Spatial
    0.96
     into
    0.95
    prep
    0.92
    spatial
    0.89
     IN
    0.88
    Activations Density 0.027%

    No Known Activations