© 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. 14827
    Prev
    Next
    INDEX
    Explanations

    personal assistant or advisor

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

    The neuron detects confirmation or subscription messages—phrases that tell you your email was successfully subscribed or that you will receive a confirmation or newsletter.

    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
     Topological
    0.71
    forRoot
    0.71
     Đế
    0.71
    实现
    0.70
     Tüm
    0.70
    實現
    0.69
     Tecnología
    0.69
    秕
    0.69
     मानते
    0.68
    的思想
    0.66
    POSITIVE LOGITS
     will
    0.87
     your
    0.82
     youre
    0.82
     ваша
    0.82
     váš
    0.79
     voicemail
    0.77
     আপনার
    0.77
     votre
    0.76
     аласыз
    0.75
    以内に
    0.75
    Activations Density 0.017%

    No Known Activations