© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130717
    Prev
    Next
    INDEX
    Explanations

    convolutional nets

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

    The neuron detects mentions of “convolution” (e.g. “Convolution,” “convolutional,” “Convolutional Nets,” etc.) in text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    9
    -2.41
    的
    -2.36
    或
    -2.33
    這個
    -2.30
    以后
    -2.22
     soste
    -2.22
    y
    -2.20
    我们的
    -2.17
    能够
    -2.16
    We
    -2.14
    POSITIVE LOGITS
    ↵
    2.36
    最后由
    2.28
    至此
    2.19
    ᯾
    2.16
    给大家
    2.16
    除此
    2.09
    媗
    2.06
     stately
    2.03
    古风
    1.98
    ll
    1.96
    Activations Density 0.006%

    No Known Activations