© 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. 39166
    Prev
    Next
    INDEX
    Explanations

    household income and population

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

    The neuron activates on mentions of “household” or “households,” especially when giving counts or statistics about them.

    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
    ↵
    -2.05
    3
    -1.69
    1
    -1.63
    your
    -1.52
    2
    -1.45
    </h2>
    -1.40
    '
    -1.36
    으
    -1.36
    0
    -1.34
     ataupun
    -1.30
    POSITIVE LOGITS
    していますが
    1.49
    襤
    1.45
    ⌣
    1.44
    凜
    1.43
    生まれ
    1.43
    本章
    1.41
     parseFrom
    1.41
     where
    1.41
     based
    1.39
    ってください
    1.38
    Activations Density 0.009%

    No Known Activations