© 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. 95751
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and variables

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

    The neuron fires on numeric constants (and simple numeric expressions) in math‐style equations.

    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
     they
    -1.20
     çünkü
    -1.09
     their
    -1.03
     until
    -0.99
     mereka
    -0.97
    ttää
    -0.96
     useAppContext
    -0.96
    vaného
    -0.95
     accessoires
    -0.94
     Він
    -0.93
    POSITIVE LOGITS
    ὺς
    1.15
     optimieren
    1.08
     provavelmente
    1.08
    шков
    1.06
     огромное
    1.05
    nell
    1.05
     behandeln
    1.04
    edakan
    1.04
    はどう
    1.04
    kawa
    1.04
    Activations Density 0.001%

    No Known Activations