© 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. 7771
    Prev
    Next
    INDEX
    Explanations

    merge or merging code changes

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

    The neuron strongly responds to standalone numeric literals—especially decimal (floating-point) numbers—scattered through technical text.

    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
    ̗
    0.57
     convirtió
    0.54
     জান
    0.50
    ètes
    0.50
     banished
    0.49
     számára
    0.48
    /-}$
    0.48
    Rf
    0.47
     sodio
    0.46
    óf
    0.46
    POSITIVE LOGITS
     merging
    1.88
    合并
    1.85
     merge
    1.84
     merger
    1.82
     merged
    1.75
    merge
    1.68
     combining
    1.65
     merges
    1.64
    合併
    1.63
    融合
    1.61
    Activations Density 0.067%

    No Known Activations