© 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. 66877
    Prev
    Next
    INDEX
    Explanations

    PID

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

    The neuron activates on occurrences of the letter sequence “PID” (in any context or casing).

    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
    1
    -3.30
    :
    -3.08
    0
    -3.06
    a
    -2.97
    4
    -2.94
    begin
    -2.83
    7
    -2.80
    ~
    -2.73
    k
    -2.64
    3
    -2.61
    POSITIVE LOGITS
     recognises
    2.86
     helicópter
    2.59
    薷
    2.52
     teaches
    2.50
    其妙
    2.42
     ZEALAND
    2.36
     anunciar
    2.34
    蜴
    2.31
     ก็
    2.30
     ajustar
    2.30
    Activations Density 0.000%

    No Known Activations