© 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. 87153
    Prev
    Next
    INDEX
    Explanations

    numbers with 5

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

    The neuron is picking out numeric tokens (multi‐digit numbers) 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_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
    </sup>
    -2.92
     ciertas
    -2.75
    %),
    -2.55
     nuovo
    -2.48
     Beobach
    -2.47
    )--
    -2.42
     senza
    -2.39
     Begleitung
    -2.39
     almeno
    -2.38
    訁
    -2.36
    POSITIVE LOGITS
    ’
    3.34
     –
    2.77
     моя
    2.23
      
    2.17
     \
    2.16
    \
    1.98
     tries
    1.95
     είναι
    1.92
    nellement
    1.90
    –
    1.89
    Activations Density 0.099%

    No Known Activations