© 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. 65340
    Prev
    Next
    INDEX
    Explanations

    Homes

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

    The neuron is specifically detecting occurrences of the word “Homes” (as used in real-estate contexts).

    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
    zelfde
    -3.38
    Ⴀ
    -2.81
    喈
    -2.77
    阇
    -2.73
    ܜ
    -2.70
    呖
    -2.69
    iocene
    -2.64
    ጴ
    -2.59
    泔
    -2.59
    骓
    -2.59
    POSITIVE LOGITS
    -
    4.09
    "
    3.81
    [
    3.23
    I
    2.78
    Instead
    2.58
    m
    2.55
    )
    2.50
    Compared
    2.50
     homes
    2.45
    If
    2.44
    Activations Density 0.006%

    No Known Activations