© 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. 34-GEMMASCOPE-RES-131K
    7. 25774
    Prev
    Next
    INDEX
    Explanations

    approximately or roughly

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

    The neuron detects quantitative/statistical information—numbers, percentages, counts, and related data‐reporting phrases—in scientific or technical text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ₱
    -0.91
     توانید
    -0.90
    iremos
    -0.87
    ágos
    -0.85
    ㎝
    -0.85
    ｃｍ
    -0.84
    ieszka
    -0.84
     beschäf
    -0.81
    __.
    -0.81
    +</
    -0.80
    POSITIVE LOGITS
     about
    3.66
     approximately
    3.63
     roughly
    2.97
    Approximately
    2.89
    約
    2.88
    approximately
    2.70
     Approximately
    2.69
     yaklaşık
    2.63
     approx
    2.58
     около
    2.58
    Activations Density 0.464%

    No Known Activations