© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130588
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on literal message strings (text inside quotes) passed to logging/printing calls (e.g. print/echo/log/Debug/info).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    actions begin or are performed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     hisz
    -1.09
    damen
    -1.05
     Mientras
    -1.01
     końca
    -1.01
     tričko
    -1.00
     mercancías
    -0.98
    fled
    -0.96
    deux
    -0.95
     méda
    -0.95
     DIG
    -0.94
    POSITIVE LOGITS
     started
    1.20
     began
    1.19
     begins
    1.04
     starts
    1.00
     in
    1.00
     ALWAYS
    0.98
     begin
    0.96
     this
    0.96
     Considering
    0.96
     start
    0.95
    Activations Density 0.006%

    No Known Activations