© 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. 2611
    Prev
    Next
    INDEX
    Explanations

    the concept of site

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

    The neuron strongly activates on words and short phrases related to “site analysis” in land‐planning or design contexts—e.g. headings and key terms like “Site,” “analysis,” “planning,” “site,” “of,” “and,” etc.—and ignores other topics.

    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
    unno
    -0.74
    都在
    -0.68
     domov
    -0.67
    places
    -0.66
    Places
    -0.66
    isan
    -0.66
     площади
    -0.66
    map
    -0.65
    ✭✭
    -0.65
    ън
    -0.63
    POSITIVE LOGITS
     site
    5.47
     sites
    3.80
    site
    3.80
    Site
    3.77
     Site
    3.64
    SITE
    3.48
     SITE
    3.31
    sites
    2.61
     سایت
    2.56
     Sites
    2.55
    Activations Density 0.036%

    No Known Activations