© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10386
    Prev
    Next
    INDEX
    Explanations

    master argument in gui constructors

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

    The main thing this neuron does is detect words referring to family relationships or kinship roles.

    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
    да
    0.82
     receive
    0.74
    যুক্ত
    0.69
    【
    0.68
    </div>
    0.68
    Benefits
    0.66
    CHAR
    0.64
    </a>
    0.61
     readily
    0.61
    서
    0.59
    POSITIVE LOGITS
     опять
    1.04
     andolan
    0.92
     Daph
    0.91
    pxy
    0.91
     Alyssa
    0.90
     phonons
    0.88
    elto
    0.86
     Nikki
    0.86
     pyrolysis
    0.86
     Nexon
    0.84
    Activations Density 0.001%

    No Known Activations