© 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. 10-GEMMASCOPE-RES-131K
    7. 40939
    Prev
    Next
    INDEX
    Explanations

    3D related terms

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

    The neuron specifically detects the “D” token in dimensional notations (e.g. “2 D,” “3 D”).

    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
     designed
    -2.69
     dubbed
    -2.67
    änemark
    -2.64
     sensed
    -2.53
     There
    -2.52
    卨
    -2.42
    巿
    -2.42
    軔
    -2.41
    émoc
    -2.41
     Both
    -2.41
    POSITIVE LOGITS
     нескольких
    2.66
     первого
    2.44
    缡
    2.41
     девя
    2.36
     quintessential
    2.36
    鲩
    2.31
     wth
    2.31
     ваш
    2.27
     dando
    2.25
     joyous
    2.23
    Activations Density 0.015%

    No Known Activations