© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5390
    Prev
    Next
    INDEX
    Explanations

    experience

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

    The neuron is triggered by first‐person self‐introductions—phrases where the speaker says “I am…” to present their own background or role.

    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_31_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
    我们要
    0.74
     우리가
    0.71
    我們要
    0.71
    我們先
    0.70
    我们就
    0.61
    我们也
    0.57
     recalled
    0.57
     we
    0.57
     આપણે
    0.56
     நமக்கு
    0.55
    POSITIVE LOGITS
     Fiverr
    1.23
     actualmente
    0.94
     attualmente
    0.93
     estoy
    0.91
     Roblox
    0.91
     tiktok
    0.91
     tengo
    0.90
     jestem
    0.88
     tutoring
    0.87
     онлайн
    0.86
    Activations Density 0.435%

    No Known Activations