© 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. 47506
    Prev
    Next
    INDEX
    Explanations

    2020, 2025, 2030, 2016, 2023, 2022

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

    Explanation of neuron 4 behavior: the main thing this neuron does is nothing—it never activates on any token.

    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
    http
    -1.20
     last
    -1.00
     previous
    -0.92
     nineteenth
    -0.85
     especially
    -0.84
    eig
    -0.84
     करता
    -0.84
     eighteenth
    -0.83
    それぞれ
    -0.82
     seventeen
    -0.82
    POSITIVE LOGITS
     Undang
    0.82
     ২
    0.81
     ۲
    0.80
     androidx
    0.80
     nogen
    0.79
    Куль
    0.79
    után
    0.78
    Наде
    0.78
     '".$
    0.78
    richtet
    0.78
    Activations Density 0.006%

    No Known Activations