© 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. 14786
    Prev
    Next
    INDEX
    Explanations

    suggesting donations or reinvestments

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

    The neuron flags language around memorial contributions and “in lieu of flowers” donation requests in obituary notices.

    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
     سنة
    0.68
    naires
    0.66
    ה
    0.66
    دو
    0.66
    ião
    0.66
    ogether
    0.65
    ദ
    0.64
    ﺪ
    0.64
    leur
    0.62
    နဲ့
    0.62
    POSITIVE LOGITS
     suggest
    0.91
    suggest
    0.84
     either
    0.82
     suggested
    0.82
    或者是
    0.80
    หรือไม่
    0.79
     sugiere
    0.79
     suggests
    0.78
     любого
    0.78
     entweder
    0.76
    Activations Density 0.013%

    No Known Activations