© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4851
    Prev
    Next
    INDEX
    Explanations

    Family

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

    The neuron strongly activates on mentions of “family” (and its plural), i.e. references to family relationships.

    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
    ܢܐ
    1.41
    Compat
    1.23
    ق
    1.20
     потер
    1.19
     collaborator
    1.18
    Couldn
    1.16
    म
    1.16
    žky
    1.15
    匮
    1.14
    ួយ
    1.13
    POSITIVE LOGITS
    👪
    1.58
    。
    1.55
    ،
    1.41
    ，
    1.27
    amp
    1.26
    ।
    1.26
    inan
    1.23
     Family
    1.20
     FAMILY
    1.17
    Relatives
    1.15
    Activations Density 0.050%

    No Known Activations