© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9263
    Prev
    Next
    INDEX
    Explanations

    family relationships

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

    The neuron activates on words naming family relationships (like “sons,” “daughters,” “brothers,” “sisters”) in obituary survivor lists.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whom
    0.57
     keeping
    0.55
    kező
    0.54
     which
    0.53
    것
    0.53
    ất
    0.52
     чего
    0.52
     Lender
    0.52
     affectionately
    0.52
    ಗೊಳ್ಳ
    0.51
    POSITIVE LOGITS
    mountain
    0.75
    quila
    0.61
     Telex
    0.61
    Telex
    0.60
    ೋತಿ
    0.59
    畬
    0.58
    Steve
    0.58
    Mountain
    0.57
    птова
    0.57
    ジム
    0.57
    Activations Density 0.001%

    No Known Activations