© 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. 10-GEMMASCOPE-RES-131K
    7. 41385
    Prev
    Next
    INDEX
    Explanations

    poder + conditional endings

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

    This neuron fires on first‐person request or requirement verbs at the start of a question (e.g. “preciso,” “tenho,” “quisiera,” “gustaría,” “podería,” etc.).

    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
    庒
    -3.20
     rosario
    -2.84
    焢
    -2.80
    檍
    -2.80
     maky
    -2.80
     otel
    -2.78
     masaj
    -2.73
    ၜ
    -2.72
     susun
    -2.70
     土産
    -2.70
    POSITIVE LOGITS
     to
    3.58
    {
    3.34
     It
    2.97
      
    2.70
     You
    2.61
     was
    2.59
    ↵↵
    2.53
     
    2.50
     be
    2.36
       
    2.22
    Activations Density 0.007%

    No Known Activations