© 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. 34-GEMMASCOPE-RES-131K
    7. 90238
    Prev
    Next
    INDEX
    Explanations

    events and actions

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

    This neuron responds to numeric and quantitative tokens (numbers, measurements, ages, dates) in factual news‐style text.

    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
     coworkers
    -1.36
     gotten
    -1.34
     еще
    -1.33
     anyways
    -1.31
     folks
    -1.31
    已然
    -1.30
     utilizes
    -1.28
     rumors
    -1.28
    Utiliz
    -1.28
     marvelous
    -1.27
    POSITIVE LOGITS
     

    1.48
     professeurs
    1.30
     bosses
    1.19
     
    1.19
      
    1.16
     personeel
    1.15
     Eigh
    1.13
    ėjimas
    1.12
     yesterday
    1.09
     tussen
    1.09
    Activations Density 0.377%

    No Known Activations