© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91480
    Prev
    Next
    INDEX
    Explanations

    mathematical variables like a, b, c, x, y

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

    This neuron fires on tokens that are parts of mathematical expressions—especially numeric constants, variable names with subscripts, and LaTeX/math markup.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    itude
    -0.89
    ricular
    -0.81
    getRepository
    -0.79
    ць
    -0.78
    bore
    -0.78
     wanita
    -0.76
     kobieta
    -0.76
     vivió
    -0.76
    vanta
    -0.74
    Specific
    -0.74
    POSITIVE LOGITS
    scar
    0.84
     where
    0.84
    닙
    0.83
     times
    0.81
    ónimo
    0.80
    できれば
    0.80
     liso
    0.79
     להת
    0.77
     trate
    0.77
     ച
    0.76
    Activations Density 0.075%

    No Known Activations