© 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. 71395
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and Spanish

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

    The neuron activates on numerical tokens (digits or numbers) in formulas or code.

    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
    ַּ
    -1.45
    ֶּ
    -1.39
    ּוֹ
    -1.37
    ִּ
    -1.25
    física
    -1.18
    Gebruik
    -1.16
    Also
    -1.15
    During
    -1.10
    Новые
    -1.09
     silencioso
    -1.09
    POSITIVE LOGITS
     to
    1.50
    乃至
    1.02
     is
    1.01
    rightarrow
    0.95
     新品
    0.94
    ordnungen
    0.91
    ēju
    0.91
     trois
    0.91
     Theologie
    0.90
    谙
    0.90
    Activations Density 0.007%

    No Known Activations