© 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. 73825
    Prev
    Next
    INDEX
    Explanations

    former employees or status

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

    The neuron strongly activates on numeric tokens—years, counts, dates, stats—i.e. it identifies numbers and numeric data in the 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
    اهد
    -0.92
    もっと
    -0.89
     egenskaper
    -0.85
    lıkla
    -0.84
    amek
    -0.79
    Население
    -0.75
    chowy
    -0.73
    autres
    -0.73
     prendra
    -0.73
    近平
    -0.72
    POSITIVE LOGITS
     former
    8.63
    Former
    6.72
    former
    6.50
     Former
    5.78
     ehemaligen
    4.84
     býval
    4.47
     formerly
    4.28
     ehemalige
    4.25
    formerly
    3.88
     бы
    3.73
    Activations Density 0.284%

    No Known Activations