© 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. 34-GEMMASCOPE-RES-131K
    7. 37813
    Prev
    Next
    INDEX
    Explanations

    pi and related mathematical constants

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

    The neuron detects numeric tokens—i.e. standalone numbers or numeric constants (multi-digit values, fractions, and numeric literals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    pelo
    -0.70
     punish
    -0.68
     polenta
    -0.67
    ssz
    -0.66
    账
    -0.65
     punished
    -0.65
    ratu
    -0.64
     PUSTAKA
    -0.64
     punishment
    -0.63
    RUM
    -0.63
    POSITIVE LOGITS
    pi
    4.97
     pi
    4.94
     PI
    4.66
     π
    4.59
    PI
    4.34
     Pi
    4.19
    π
    4.13
    Pi
    3.78
    
    2.97
    𝜋
    2.88
    Activations Density 0.178%

    No Known Activations