© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66766
    Prev
    Next
    INDEX
    Explanations

    algebraic expressions with sqrt

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

    This neuron fires on numeric constants appearing as exponents or in exponential‐type expressions in mathematical formulas.

    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
     selva
    -1.04
    dication
    -1.00
     avenir
    -0.97
     内衣
    -0.96
    Martinez
    -0.93
     børn
    -0.93
    omato
    -0.93
    ерт
    -0.92
    dddd
    -0.91
     समस्या
    -0.91
    POSITIVE LOGITS
     our
    1.25
     earlier
    1.04
     just
    1.03
     other
    1.01
     those
    0.94
     prior
    0.94
     we
    0.94
     Prior
    0.94
     older
    0.91
     These
    0.90
    Activations Density 0.024%

    No Known Activations