© 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. 55784
    Prev
    Next
    INDEX
    Explanations

    covered by, with, or in

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

    The neuron specifically activates on instances of the word “covered.”

    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
    </i>
    -0.93
    梛
    -0.89
    ни
    -0.88
    ギター
    -0.84
     into
    -0.82
    KeyType
    -0.82
    𓐍
    -0.81
     vzdu
    -0.79
     ナイ
    -0.79
     clutching
    -0.78
    POSITIVE LOGITS
    tly
    1.49
     Covered
    1.39
     covered
    1.35
    Covered
    1.17
     Covers
    1.17
     Cover
    1.16
     covers
    1.11
    covers
    1.03
     covering
    1.00
    covered
    0.98
    Activations Density 0.016%

    No Known Activations