© 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. 1585
    Prev
    Next
    INDEX
    Explanations

    family and relations

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

    The main thing this neuron does is detect mentions of family or kinship (e.g., “family,” “relations,” “generations,” “matriarch”).

    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
    </b>
    -1.48
    {
    -1.38
    </code>
    -1.36
    ].
    -1.36
    </i>
    -1.34
    </h1>
    -1.24
    ↵↵↵↵
    -1.23
    </th>
    -1.22
    ↵↵↵
    -1.22
    /**
    -1.20
    POSITIVE LOGITS
     afterward
    1.38
    family
    1.23
     afterwards
    1.22
     familiale
    1.20
     thus
    1.20
    できるので
    1.20
     trattano
    1.18
     after
    1.17
     thereafter
    1.17
     carbón
    1.16
    Activations Density 0.029%

    No Known Activations