© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72708
    Prev
    Next
    INDEX
    Explanations

    kinship and kindred relations

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

    The neuron strongly activates on words and morphemes related to family ties—e.g. “kin,” “kindred,” “kinship,” and “kins.”

    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
    𓋼
    -2.86
    髡
    -2.31
     Mehrheit
    -2.30
    𝐞
    -2.28
    塍
    -2.23
    );
    -2.19
     zakup
    -2.14
    </h3>
    -2.11
    戆
    -2.08
    你喜欢
    -2.05
    POSITIVE LOGITS
    不像
    2.47
    ’
    2.42
    /
    2.38
    *
    2.38
    2
    2.38
    \
    2.38
     那
    2.19
     But
    2.19
    at
    2.19
    Y
    2.13
    Activations Density 0.007%

    No Known Activations