© 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. 22-GEMMASCOPE-RES-131K
    7. 12859
    Prev
    Next
    INDEX
    Explanations

    numbers, punctuation, and copyright notices

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

    This neuron fires on numeric tokens used in reference citations (e.g. chapter and verse numbers in Bible-style references).

    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
     that
    -1.41
    HttpEntity
    -1.16
     would
    -1.15
     like
    -1.12
    篁
    -1.10
     delgada
    -1.07
    噫
    -1.06
     at
    -1.05
     through
    -1.05
     develop
    -1.02
    POSITIVE LOGITS
     certaines
    1.13
     distr
    1.10
     zweimal
    1.09
    oczes
    1.08
     новых
    1.06
     einzelnen
    1.04
     ruine
    1.03
     certamente
    1.02
     広場
    1.00
     propone
    0.98
    Activations Density 0.002%

    No Known Activations