© 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. 45124
    Prev
    Next
    INDEX
    Explanations

    political chairperson

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

    The neuron fires on low‐frequency, content‐bearing single tokens—especially proper names, official titles (e.g. “chairperson”), and other uncommon vocabulary.

    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
    s
    -2.95
    衕
    -2.56
    鏷
    -2.55
    茕
    -2.53
     voor
    -2.50
    柃
    -2.48
     вернулся
    -2.39
    熊猫
    -2.39
    -2.31
    re
    -2.28
    POSITIVE LOGITS
            
    2.53
     Fifteen
    2.31
     Thirty
    2.31
    According
    2.25
     mehrere
    2.11
    The
    2.09
     mehreren
    2.06
     necessaria
    2.06
    Compared
    2.05
     fizeram
    2.05
    Activations Density 0.002%

    No Known Activations