© 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. 130970
    Prev
    Next
    INDEX
    Explanations

    discussing couples

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

    The neuron strongly activates on occurrences of the word “couples.”

    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
    {
    -2.56
     '
    -2.45
    ."
    -2.44
     dritte
    -2.42
    ༀ
    -2.25
    絎
    -2.20
     evo
    -2.20
     exceptionally
    -2.13
     apreci
    -2.03
    traueranzeige
    -2.00
    POSITIVE LOGITS
    al
    3.09
    when
    2.94
     Also
    2.63
    their
    2.48
    from
    2.45
    尓
    2.36
    ton
    2.22
     また
    2.20
    </td>
    2.14
     setPassword
    2.14
    Activations Density 0.008%

    No Known Activations