© 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. 9619
    Prev
    Next
    INDEX
    Explanations

    lambda functions operating on lists

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

    The neuron strongly activates on second-person address—i.e. occurrences of “you” (directly addressing the reader).

    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
    ли
    0.94
    iak
    0.86
    侣
    0.82
    au
    0.82
     hablaremos
    0.79
    サーバー
    0.77
     ninguna
    0.76
     çöze
    0.76
    遥
    0.75
    ar
    0.73
    POSITIVE LOGITS
     Radial
    0.79
    ⓓ
    0.78
    tica
    0.76
    Creators
    0.70
    mathbb
    0.68
    म्मद
    0.67
     noodles
    0.66
     এক্ষেত্রে
    0.65
    Bots
    0.65
    AlignedText
    0.64
    Activations Density 0.001%

    No Known Activations