© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13138
    Prev
    Next
    INDEX
    Explanations

    code structure or punctuation

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

    The neuron activates on numerical tokens – it flags numbers (integers or decimals) appearing in the 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_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
     einigen
    -0.88
     einzigartige
    -0.87
    marino
    -0.78
    ragamo
    -0.78
     Jugendliche
    -0.77
     năm
    -0.76
    inoza
    -0.76
     добраться
    -0.76
    Inoltre
    -0.76
     желание
    -0.76
    POSITIVE LOGITS
    ````
    0.89
    homem
    0.87
     vik
    0.86
     uren
    0.86
    룹
    0.81
     licha
    0.81
     icke
    0.80
     noire
    0.80
     accedere
    0.77
    という
    0.77
    Activations Density 0.018%

    No Known Activations