© 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. 22-GEMMASCOPE-RES-131K
    7. 129578
    Prev
    Next
    INDEX
    Explanations

    The neuron detects occurrences of the word “spending” (i.e. mentions of financial expenditure).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    money spending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    籏
    -2.64
    l
    -2.56
    </b>
    -2.52
    笑容
    -2.17
    f
    -2.13
    場合には
    -2.11
     continue
    -2.09
    n
    -2.08
    有不少
    -2.05
    ꞈ
    -2.02
    POSITIVE LOGITS
    <bos>
    2.41
     Atau
    2.17
    ₶
    2.16
    呓
    2.13
    ronesia
    2.11
    淩
    2.09
    ⭏
    2.06
     сист
    2.02
     风景
    2.00
    tigheter
    2.00
    Activations Density 0.008%

    No Known Activations