© 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. 48516
    Prev
    Next
    INDEX
    Explanations

    his anniversary or birthday

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

    The main thing this neuron does is detect numerical tokens (digits and numbers, especially those used in dates or counts).

    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
     then
    -1.66
     geluid
    -1.48
     bekijken
    -1.43
     ligera
    -1.38
     daarbij
    -1.34
     Під
    -1.34
    ありません
    -1.31
    绶
    -1.31
    でございます
    -1.30
     Nguy
    -1.29
    POSITIVE LOGITS
     använd
    1.43
     проведе
    1.41
    ]
    1.39
     vitale
    1.38
    |
    1.36
    ± 
    1.33
     セーター
    1.32
    ，
    1.30
     qualsiasi
    1.30
    FOTOS
    1.29
    Activations Density 0.034%

    No Known Activations