© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12013
    Prev
    Next
    INDEX
    Explanations

    telling or predicting action

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

    This neuron detects verbs of obtaining or choosing—especially different forms of “get” and “pick.”

    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
    创新
    0.73
    ním
    0.71
    𝘁
    0.70
     बोलते
    0.68
    𝑝
    0.68
    𝗖
    0.67
    pedido
    0.66
    绩
    0.66
    据悉
    0.66
    Გ
    0.66
    POSITIVE LOGITS
     chances
    0.61
     irgendwo
    0.61
     losers
    0.60
     Gelegenheit
    0.58
     spots
    0.58
     quarrels
    0.58
     (
    0.56
     anderer
    0.56
     folks
    0.55
     glimpses
    0.55
    Activations Density 0.557%

    No Known Activations