© 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. 24-GEMMASCOPE-2-RES-16K
    7. 2414
    Prev
    Next
    INDEX
    Explanations

    certain concluding phrases

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

    The neuron fires on words naming people in one’s social or family circle (e.g. guardians, spouses, children, friends).

    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
    ॉन
    0.61
    క్‌
    0.57
    barui
    0.54
    ϲ
    0.54
     असून
    0.53
    𝗿
    0.53
    ⑮
    0.51
    క్
    0.50
    𝑐
    0.50
    —”
    0.49
    POSITIVE LOGITS
    (?)
    0.79
     viendo
    0.73
     porque
    0.70
     I
    0.69
     Porque
    0.68
     cosas
    0.67
     pois
    0.67
     Leute
    0.67
     skoro
    0.67
     (?)
    0.66
    Activations Density 0.249%

    No Known Activations