© 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. 68816
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations

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

    This neuron activates on individual numeric tokens (single‐digit numbers) within mathematical expressions.

    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
     silencioso
    -1.09
     они
    -1.09
     pieles
    -1.06
    زال
    -1.05
    zapatillas
    -1.05
     たち
    -1.04
    جين
    -1.02
     somos
    -1.02
    mizuno
    -1.02
     景色
    -1.00
    POSITIVE LOGITS
    v
    1.18
    ↵
    1.05
    at
    1.03
    などを
    1.02
    ol
    0.96
    CF
    0.94
     Tatsache
    0.93
    RC
    0.93
    msg
    0.93
    IP
    0.92
    Activations Density 0.067%

    No Known Activations