© 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. 34-GEMMASCOPE-RES-131K
    7. 106842
    Prev
    Next
    INDEX
    Explanations

    origin or position

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

    The neuron strongly activates on spatial prepositions and adverbs (e.g. “from,” “beneath,” “outside”) indicating origin or position.

    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
    according
    -0.96
    到
    -0.94
     οποίο
    -0.93
     шесть
    -0.91
    直到
    -0.90
    bia
    -0.89
     According
    -0.88
     потому
    -0.88
    所有的
    -0.85
    everything
    -0.85
    POSITIVE LOGITS
     behind
    2.39
     within
    2.34
     beneath
    2.33
     inside
    2.13
     afar
    1.99
     atop
    1.96
     beside
    1.88
     beyond
    1.86
     underneath
    1.77
     below
    1.71
    Activations Density 0.077%

    No Known Activations