© 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. 73896
    Prev
    Next
    INDEX
    Explanations

    DOM elements and nodes

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

    The neuron fires strongly on occurrences of the substring “dom” (e.g. in variable names, function parameters, or import paths).

    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
     vorigen
    -2.36
     said
    -2.30
    .”
    -2.28
    </i>
    -2.22
     Vorgang
    -2.16
     Veränder
    -2.06
     chiama
    -2.06
    蟜
    -1.99
    </h5>
    -1.97
     enjoyed
    -1.96
    POSITIVE LOGITS
    {
    2.50
    我了
    2.09
    熜
    2.08
     these
    2.05
    麦克
    1.98
    近年来
    1.84
    克兰
    1.81
    ㉕
    1.80
    了我
    1.80
    荷兰
    1.79
    Activations Density 0.005%

    No Known Activations