© 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. 85047
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

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

    The neuron strongly activates on large, round numeric tokens (notably “1000”-type numbers with trailing zeros).

    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
    䜣
    -2.50
    5
    -2.47
    7
    -2.44
    The
    -2.22
     üblichen
    -2.22
    4
    -2.17
     ส์
    -2.14
    2
    -2.13
     Handlungen
    -2.09
     Sünden
    -2.08
    POSITIVE LOGITS
    ⽼
    2.81
    遄
    2.23
     testa
    2.13
    🔸
    2.11
    ↵
    2.09
     voca
    2.08
     bayer
    2.06
    🔹
    2.05
    that
    1.97
     fio
    1.96
    Activations Density 0.035%

    No Known Activations