© 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. 2391
    Prev
    Next
    INDEX
    Explanations

    your idea or guidelines

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

    This neuron detects direct address to the reader, i.e. second-person pronouns like “you” and “your.”

    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
    during
    0.56
    работа
    0.55
     ملی
    0.55
     pli
    0.55
     всей
    0.54
    一座
    0.54
     sebuah
    0.53
    帷
    0.52
     peruse
    0.51
     לנו
    0.51
    POSITIVE LOGITS
     언급
    0.80
     statement
    0.78
     বক্তব্যের
    0.76
     misunder
    0.75
     statements
    0.75
     seems
    0.75
     Aussage
    0.73
    提到的
    0.73
     말씀
    0.73
    님의
    0.72
    Activations Density 0.276%

    No Known Activations