© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66905
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and polynomials

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

    The neuron activates on mentions of named mathematical functions—especially Greek-letter functions like ζ (zeta) or χ (chi).

    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
     who
    -1.24
    lbs
    -1.09
    راع
    -1.08
    cora
    -1.07
     climático
    -1.05
     italiani
    -1.05
    気に入りの
    -1.05
     amount
    -1.03
     criteria
    -1.01
     partito
    -1.01
    POSITIVE LOGITS
    تفسير
    1.23
    Monika
    1.20
    //*/
    1.16
    Gid
    1.14
    Synonym
    1.13
     Boletín
    1.08
    Harald
    1.05
     Apro
    1.05
    Peacock
    1.05
     brevemente
    1.03
    Activations Density 0.009%

    No Known Activations