© 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. 33152
    Prev
    Next
    INDEX
    Explanations

    solving mathematical equations

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

    The neuron activates on numeric quantities (especially decimal numbers and measurements).

    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
     vart
    -0.88
     not
    -0.88
    ÍAS
    -0.86
     Мексика
    -0.82
    鉿
    -0.81
    Suicide
    -0.80
     kull
    -0.79
    tahu
    -0.79
     магазине
    -0.77
    Auswahl
    -0.76
    POSITIVE LOGITS
     solving
    1.27
     solve
    1.22
     solution
    1.09
     solves
    1.03
     Solving
    1.02
     figuring
    1.01
    posals
    0.98
     solved
    0.94
    solve
    0.94
    τικής
    0.90
    Activations Density 0.065%

    No Known Activations