© 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. 10-GEMMASCOPE-RES-131K
    7. 42160
    Prev
    Next
    INDEX
    Explanations

    welfare and social services

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

    The neuron fires on occurrences of the word “welfare.”

    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
    '
    -3.39
     was
    -2.88
    "}}>
    -2.58
    訁
    -2.42
     ซึ่ง
    -2.41
     "
    -2.34
     startling
    -2.28
    餿
    -2.25
    一旁的
    -2.23
     overwhelming
    -2.20
    POSITIVE LOGITS
    o
    3.06
    This
    2.88
    These
    2.66
    bernador
    2.53
    lgari
    2.52
    ༔
    2.44
    they
    2.36
    стями
    2.36
     незавер
    2.36
    事は
    2.34
    Activations Density 0.003%

    No Known Activations