© 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. 34-GEMMASCOPE-RES-131K
    7. 47421
    Prev
    Next
    INDEX
    Explanations

    quadratic and parabolic forms

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

    This neuron specifically fires on occurrences of the word “quadratic.”

    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
    ंज
    -0.72
    }>\
    -0.71
    Cactus
    -0.68
    vanie
    -0.68
     Cactus
    -0.68
     EPL
    -0.68
    Kant
    -0.66
    挨
    -0.66
     सा
    -0.65
     BOUND
    -0.65
    POSITIVE LOGITS
     parabola
    1.52
     vertex
    1.45
     parabolic
    1.41
    Vertex
    1.32
     parab
    1.31
     Parab
    1.27
     quadratic
    1.27
    vertex
    1.26
     Vertex
    1.25
    Parab
    1.21
    Activations Density 0.023%

    No Known Activations