© 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. 75639
    Prev
    Next
    INDEX
    Explanations

    inverter and submarine

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

    The neuron primarily detects occurrences of the technical term “inverter.”

    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
    ine
    -3.09
    0
    -2.89
    which
    -2.84
    橚
    -2.69
    嫱
    -2.64
    but
    -2.53
     regards
    -2.53
    ut
    -2.52
    la
    -2.52
    だけです
    -2.45
    POSITIVE LOGITS
    ↵↵
    2.39
     欣赏
    2.36
            
    2.34
    𝄆
    2.28
    至尊
    2.27
     Those
    2.23
     млрд
    2.23
     olvidar
    2.19
     cuando
    2.17
     stát
    2.17
    Activations Density 0.016%

    No Known Activations