© 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. 10-GEMMASCOPE-RES-131K
    7. 67207
    Prev
    Next
    INDEX
    Explanations

    near followed by a noun or location

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

    The neuron fires on expressions of measured proximity—numbers (often with “near”) that specify distances or coordinates.

    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
    ти
    -2.00
    {
    -1.86
    ).
    -1.85
    ка
    -1.82
    isation
    -1.80
    In
    -1.76
    ,
    -1.73
     stato
    -1.73
    …”
    -1.71
    ANG
    -1.70
    POSITIVE LOGITS
     Füßen
    2.36
     the
    2.33
     They
    2.03
     them
    2.00
     themselves
    1.86
     harten
    1.85
     понял
    1.85
     teneur
    1.81
     Their
    1.80
     $^{
    1.79
    Activations Density 0.044%

    No Known Activations