© 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. 3601
    Prev
    Next
    INDEX
    Explanations

    punctuation and code separators

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

    The neuron fires on numeric literals in code (digits, numbers, and numeric constants).

    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
     innych
    -1.90
     других
    -1.67
     інших
    -1.62
    其他的
    -1.59
     інші
    -1.56
     autre
    -1.54
     outras
    -1.53
    いっ
    -1.52
    過ぎて
    -1.46
    Otros
    -1.45
    POSITIVE LOGITS
     this
    2.03
     that
    1.66
    viating
    1.37
    schrank
    1.34
    縂
    1.33
    ড
    1.32
     having
    1.29
     sicuramente
    1.28
    ницу
    1.26
    쑥
    1.24
    Activations Density 0.011%

    No Known Activations