© 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. 67719
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

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

    This neuron specifically activates on multi‐digit numeric tokens (numbers appearing in equations, equation labels, or other math expressions).

    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
    strator
    -1.21
     first
    -1.09
    ようですが
    -1.05
    –
    -1.05
    Angebot
    -1.04
     zerstört
    -1.02
     tersebut
    -1.00
    chea
    -1.00
    Other
    -0.99
    𝛼
    -0.98
    POSITIVE LOGITS
    大多
    1.01
     costs
    1.00
     ۱۳۹
    0.97
     net
    0.96
     likelihood
    0.96
    ablanca
    0.95
     lorsqu
    0.94
     kompleks
    0.93
     Tongue
    0.93
    ramientas
    0.93
    Activations Density 0.008%

    No Known Activations