© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10831
    Prev
    Next
    INDEX
    Explanations

    imposes values upon

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

    This neuron responds to words that denote authoritative imposition or enforcement (e.g. imposed, imposed penalties, dictated, enforced, regulation, condition).

    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
    ẋ
    0.51
    廷
    0.50
    πη
    0.49
    guas
    0.48
    irinha
    0.48
    握
    0.48
    erry
    0.48
    sli
    0.48
    TRIGGER
    0.48
    빤
    0.46
    POSITIVE LOGITS
     upon
    2.27
    Upon
    2.00
     Upon
    1.98
    upon
    1.98
     onto
    1.94
     asupra
    1.81
     върху
    1.70
     عليهم
    1.68
    onto
    1.44
     عليه
    1.44
    Activations Density 0.380%

    No Known Activations