© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11024
    Prev
    Next
    INDEX
    Explanations

    company names and abbreviations

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

    This neuron activates on proper names and acronyms (e.g. brand names, people’s names, organizational or technical abbreviations).

    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
     But
    -4.22
     tetapi
    -3.16
     pero
    -3.06
     nhưng
    -2.91
     lakini
    -2.70
    .”
    -2.59
    甃
    -2.55
     maar
    -2.48
     mayoría
    -2.47
     אבל
    -2.45
    POSITIVE LOGITS
    抬手
    2.66
    薆
    2.48
    婠
    2.45
    you
    2.42
    㐂
    2.36
    觔
    2.31
    Ꭳ
    2.28
     وط
    2.27
    
    2.23
    姈
    2.23
    Activations Density 0.009%

    No Known Activations