© 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. 28246
    Prev
    Next
    INDEX
    Explanations

    numbers and references

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

    The main thing this neuron does is detect standalone numeric literals (digits or 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_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
     then
    -1.01
    suddenly
    -0.97
    THEN
    -0.92
    remaining
    -0.90
    Etat
    -0.88
     памяти
    -0.87
     montes
    -0.87
    綃
    -0.86
    acknowled
    -0.86
     collè
    -0.85
    POSITIVE LOGITS
     by
    1.52
     first
    0.98
     också
    0.96
     for
    0.96
     both
    0.89
     through
    0.86
    ｦ
    0.85
     like
    0.84
     båda
    0.84
     says
    0.84
    Activations Density 0.001%

    No Known Activations