© 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. 75462
    Prev
    Next
    INDEX
    Explanations

    series

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

    The neuron fires on numeric tokens—especially model or series numbers (e.g. “7,” “5,” “2368,” etc.).

    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
    鑁
    -1.35
     mariposas
    -1.27
    廰
    -1.19
     indiví
    -1.16
    ственная
    -1.16
     家居
    -1.13
    ୃ
    -1.12
    眛
    -1.11
     própri
    -1.11
    ارتمان
    -1.09
    POSITIVE LOGITS
     Series
    1.57
     series
    1.57
    series
    1.44
    Series
    1.41
    re
    1.13
    f
    1.09
    .”
    1.08
    en
    1.07
     serie
    1.05
     сери
    1.05
    Activations Density 0.023%

    No Known Activations