© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82679
    Prev
    Next
    INDEX
    Explanations

    consumer financial protection

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

    The neuron fires strongly on multiword “consumer” collocations—e.g. Consumer Watchdog, Consumer Protection, or consumer-directed health care.

    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
    ineas
    -0.84
    ❤️
    -0.83
    митри
    -0.81
     poté
    -0.78
     torna
    -0.77
    晴れ
    -0.76
     primas
    -0.75
     фаса
    -0.74
    メガネ
    -0.73
    驰
    -0.72
    POSITIVE LOGITS
     Consumer
    0.93
     tirs
    0.73
     スーツ
    0.73
    ighbor
    0.71
     Cracks
    0.71
     ampliamente
    0.70
     ottenuto
    0.70
     چیه
    0.70
    lliant
    0.70
    기에
    0.70
    Activations Density 0.013%

    No Known Activations