© 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. 1859
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

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

    The neuron is picking out negative numeric constants (large-magnitude negative coefficients) in mathematical expressions.

    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
    0
    -2.23
    l
    -2.14
    </h3>
    -1.95
    </strong>
    -1.88
    ri
    -1.82
    b
    -1.81
    4
    -1.77
    3
    -1.73
     schnellen
    -1.66
    g
    -1.66
    POSITIVE LOGITS
     it
    1.94
    骓
    1.79
    หรือ
    1.73
    ⩴
    1.66
    Xna
    1.65
    選べる
    1.58
     one
    1.47
    会儿
    1.45
    媵
    1.45
     pensar
    1.43
    Activations Density 0.048%

    No Known Activations