© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69446
    Prev
    Next
    INDEX
    Explanations

    Advertisement or Q following

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

    The neuron detects “ADVERTISEMENT” markers (i.e. ad‐break labels) in the 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
     who
    -1.75
    罴
    -1.69
     for
    -1.66
     rainha
    -1.57
     so
    -1.53
    铼
    -1.53
    了很多
    -1.48
     where
    -1.47
    ৄ
    -1.47
    佉
    -1.45
    POSITIVE LOGITS
    梛
    1.69
     chanteuse
    1.52
    或者
    1.47
     یا
    1.47
    </strong>
    1.45
     appétit
    1.45
    ーーーー
    1.44
     или
    1.42
    䊳
    1.42
    孩子们
    1.41
    Activations Density 0.001%

    No Known Activations