© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112364
    Prev
    Next
    INDEX
    Explanations

    brothers and sisters

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

    The neuron detects mentions of siblings, specifically the words “brothers” and “sisters.”

    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
    {
    -2.84
    ed
    -2.14
    ating
    -2.09
    死的
    -1.92
     Euer
    -1.87
    ه
    -1.80
    er
    -1.79
    i
    -1.74
     voordat
    -1.70
    t
    -1.70
    POSITIVE LOGITS
     brothers
    2.63
    s
    2.33
    </td>
    2.23
    gdala
    2.14
    +};
    2.09
    anceled
    2.08
    ']
    2.05
    }{
    2.05
     cheminée
    2.00
    畯
    1.99
    Activations Density 0.003%

    No Known Activations