© 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. 73524
    Prev
    Next
    INDEX
    Explanations

    arithmetic calculations and sequences

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

    The neuron strongly activates on the numeric answer tokens (the computed results) in these math‐problem statements.

    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
    喩
    -0.99
     岁
    -0.93
     already
    -0.90
     Verpflichtung
    -0.90
     if
    -0.89
    みてください
    -0.89
    dams
    -0.89
    矢量
    -0.88
    してみてください
    -0.88
    示意图
    -0.85
    POSITIVE LOGITS
    Gön
    1.09
     dergleichen
    1.02
    یریت
    0.98
    ERVIS
    0.97
    espacio
    0.96
    ximate
    0.96
    を変える
    0.95
     opravdu
    0.94
     regresa
    0.94
     retraso
    0.94
    Activations Density 0.006%

    No Known Activations