© 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. 67722
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and formulas

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

    The neuron fires on numeric constants, variables, and scientific symbols in 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
    ैन
    -0.77
    وفاته
    -0.75
    rollment
    -0.73
     venue
    -0.73
     EVP
    -0.73
     ^_^
    -0.72
    danno
    -0.71
    Schritt
    -0.71
    基本的に
    -0.71
    文分享
    -0.70
    POSITIVE LOGITS
     tambahan
    0.84
     not
    0.84
     why
    0.81
     average
    0.81
     Average
    0.77
     dahulu
    0.75
    Wins
    0.75
     family
    0.75
     North
    0.75
     ज्ञ
    0.74
    Activations Density 0.022%

    No Known Activations