© 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. 129163
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric constants in mathematical expressions.

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

    mathematical expressions and equations

    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
    قق
    -0.86
     how
    -0.84
     in
    -0.84
     nue
    -0.82
     only
    -0.81
    ;
    -0.80
     to
    -0.79
     auteurs
    -0.78
    FormBuilder
    -0.78
    ضا
    -0.77
    POSITIVE LOGITS
     prêts
    1.02
     meistens
    1.01
     éte
    0.99
     produite
    0.97
     producir
    0.95
     interak
    0.95
     cráneo
    0.94
     sentirse
    0.93
     skoro
    0.93
    RODU
    0.93
    Activations Density 0.013%

    No Known Activations