© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128995
    Prev
    Next
    INDEX
    Explanations

    The neuron is selectively activating on numeric constants (and adjacent arithmetic symbols) within mathematical/formulaic text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mathematical symbols and operators

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     quelcon
    -1.12
     叶子
    -1.08
     temporaire
    -1.07
     admitir
    -1.04
     daran
    -1.02
     方案
    -1.02
     orgánica
    -1.02
     perpé
    -1.02
     ngay
    -1.02
    här
    -1.00
    POSITIVE LOGITS
     in
    1.27
    quelize
    1.19
     with
    1.18
    èbres
    1.15
     like
    1.11
    órica
    1.10
    :^(
    1.06
    Ї
    1.03
     would
    1.03
    íí
    1.01
    Activations Density 0.020%

    No Known Activations