© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7132
    Prev
    Next
    INDEX
    Explanations

    what is between

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

    The neuron detects formal “A [term] …” definition statements, especially legal or contractual definitions.

    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
    /*
    0.74
     दिसून
    0.66
     tedy
    0.59
     obviously
    0.58
     certainly
    0.58
     evidently
    0.56
     DISCUSSION
    0.55
     Maitland
    0.55
     implications
    0.54
     इंपॉर्ट
    0.54
    POSITIVE LOGITS
     bacterium
    0.70
     rebirth
    0.66
     agrupación
    0.64
    ዠ
    0.64
    smallest
    0.63
    deleteOne
    0.63
     padre
    0.63
     máquinas
    0.63
     lubricant
    0.62
     velocidade
    0.62
    Activations Density 0.161%

    No Known Activations