© 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. 2777
    Prev
    Next
    INDEX
    Explanations

    communication and transmission of molecules

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

    The neuron fires on words that denote the act of propagating or sending something onward—verbs like “spread,” “transmitted,” “promote,” or “spreading.”

    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
    acketing
    0.59
    চ্ছন্দ
    0.54
     ഖ
    0.53
     calendrier
    0.53
    웰
    0.52
     പരിശോധ
    0.52
     prét
    0.50
    <unused2162>
    0.50
     سامنا
    0.50
     chromed
    0.49
    POSITIVE LOGITS
     переда
    2.89
    传递
    2.73
    傳
    2.59
    传播
    2.58
    传
    2.56
     transmission
    2.52
     передачи
    2.44
     transmitted
    2.42
    transmission
    2.41
     truyền
    2.39
    Activations Density 0.887%

    No Known Activations