© 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. 733
    Prev
    Next
    INDEX
    Explanations

    The neuron responds strongly to action verbs that denote influencing or assisting (e.g. “affect,” “help”).

    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
    Д
    0.56
    быз
    0.55
     solutes
    0.55
     ballistic
    0.54
     sẻ
    0.54
    الى
    0.51
     principalTable
    0.50
    
    0.50
     calculi
    0.49
     convolutional
    0.48
    POSITIVE LOGITS
     decidido
    0.60
    お客
    0.59
    お子
    0.59
    ાઇન
    0.58
     влияет
    0.57
    你在
    0.57
     meinem
    0.56
     mensen
    0.55
     vás
    0.55
     вашего
    0.54
    Activations Density 0.000%

    No Known Activations