© 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. 108095
    Prev
    Next
    INDEX
    Explanations

    piezoelectric materials and effects

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

    The neuron fires strongly on bibliographic citation and document‐title elements (e.g. journal names, volume/issue numbers, dates, and other reference formatting) in scientific texts.

    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
    şil
    -0.86
    hea
    -0.83
    }_{\
    -0.77
    limb
    -0.77
    rtner
    -0.76
     JFrame
    -0.75
     invited
    -0.73
    //}
    -0.72
     IMMEDIATE
    -0.72
    μα
    -0.71
    POSITIVE LOGITS
    pie
    1.30
     Pie
    1.25
    Pie
    1.13
     piezoelectric
    1.13
     piezo
    1.09
     pie
    1.05
     SAW
    1.00
    PIE
    0.96
     PZ
    0.94
     пье
    0.89
    Activations Density 0.060%

    No Known Activations