© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2981
    Prev
    Next
    INDEX
    Explanations

    son, founder, descendant, heir

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

    The neuron responds strongly to capitalized proper nouns and named entities (people’s names, titles, places, etc.).

    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_31_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
     pantalones
    0.67
     snappy
    0.66
    ביע
    0.66
    ாக்கு
    0.65
    ண்கள்
    0.64
    ங்கம்
    0.64
     vélo
    0.63
    ার্জি
    0.62
    燚
    0.62
    泱
    0.61
    POSITIVE LOGITS
     ibn
    1.05
     oğlu
    1.01
     figlio
    0.89
     grandson
    0.86
     hijo
    0.84
     (†
    0.80
     сын
    0.79
    の子
    0.78
     nobleman
    0.77
     daughter
    0.76
    Activations Density 0.232%

    No Known Activations