© 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. 34-GEMMASCOPE-RES-131K
    7. 81139
    Prev
    Next
    INDEX
    Explanations

    android:id attribute

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

    The neuron does not respond to any tokens in these XML fragments—it fails to detect any particular pattern and remains inactive.

    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
     Scientist
    -0.84
     già
    -0.79
     tweeted
    -0.78
     Professor
    -0.77
    alis
    -0.77
     unveiled
    -0.76
     snorkel
    -0.76
    IQUE
    -0.76
     Seville
    -0.75
    stamo
    -0.75
    POSITIVE LOGITS
    cky
    0.76
    ebly
    0.75
     oil
    0.75
    qai
    0.74
    peed
    0.73
    czenie
    0.71
    ._.
    0.71
     few
    0.71
    ̕
    0.70
     many
    0.69
    Activations Density 0.006%

    No Known Activations